benchbench / cache /agreements_cache_230b5a189df3af8cde801ce251b7b2ef.csv
Yotam-Perlitz
revise cache
292d764
raw
history blame
174 kB
scenario,scenario_source,ref_scenario,ref_source,corr_type,model_select_strategy,model_subset_size_requested,exp_n,correlation,p_value
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6,0.016666115520282188
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,1,0.5555555555555555,0.02860945767195767
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6888888888888888,0.00468694885361552
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6,0.016666115520282188
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,4,0.6444444444444444,0.009148478835978836
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6,0.016666115520282188
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,6,0.6,0.016666115520282188
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6,0.016666115520282188
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6,0.016666115520282188
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6,0.016666115520282188
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,0,0.22473328748774735,0.36917141633269157
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,1,0.15555555555555553,0.6006536596119929
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,2,0.3146266024828463,0.2086677876982641
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,3,0.22473328748774735,0.36917141633269157
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,4,0.3146266024828463,0.2086677876982641
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,5,0.15555555555555553,0.6006536596119929
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,6,0.3146266024828463,0.2086677876982641
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,7,0.22473328748774735,0.36917141633269157
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,8,0.22473328748774735,0.36917141633269157
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,9,0.15555555555555553,0.6006536596119929
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,0,0.3333333333333333,0.21637345679012346
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,1,0.19999999999999998,0.4843127204585538
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,2,0.4222222222222222,0.10831349206349207
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,3,0.3333333333333333,0.21637345679012346
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,4,0.4222222222222222,0.10831349206349207
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,5,0.19999999999999998,0.4843127204585538
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,6,0.4222222222222222,0.10831349206349207
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,7,0.3333333333333333,0.21637345679012346
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,8,0.3333333333333333,0.21637345679012346
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,9,0.19999999999999998,0.4843127204585538
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6,0.016666115520282188
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,1,0.4222222222222222,0.10831349206349207
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6444444444444444,0.009148478835978836
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,3,0.5111111111111111,0.04662257495590829
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,4,0.6,0.016666115520282188
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,5,0.4666666666666666,0.07255015432098766
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,6,0.6444444444444444,0.009148478835978836
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,7,0.5111111111111111,0.04662257495590829
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6,0.016666115520282188
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,9,0.4666666666666666,0.07255015432098766
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,1,0.7333333333333333,0.002212852733686067
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7333333333333333,0.002212852733686067
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,4,0.7333333333333333,0.002212852733686067
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,6,0.7333333333333333,0.002212852733686067
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,7,0.8222222222222221,0.0003576940035273369
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,0,0.7191465199607915,0.004057136032371292
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,1,0.6,0.016666115520282188
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6292532049656926,0.011921001496914019
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,3,0.5393598899705937,0.03114121059579671
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,4,0.6292532049656926,0.011921001496914019
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6,0.016666115520282188
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,6,0.6292532049656926,0.011921001496914019
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,7,0.5393598899705937,0.03114121059579671
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,8,0.7191465199607915,0.004057136032371292
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6,0.016666115520282188
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,0,0.4222222222222222,0.10831349206349207
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,1,0.4222222222222222,0.10831349206349207
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,2,0.4222222222222222,0.10831349206349207
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,3,0.37777777777777777,0.1557418430335097
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,4,0.4666666666666666,0.07255015432098766
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,5,0.4666666666666666,0.07255015432098766
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,6,0.28888888888888886,0.2912483465608466
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,7,0.37777777777777777,0.1557418430335097
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,8,0.4222222222222222,0.10831349206349207
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,9,0.4666666666666666,0.07255015432098766
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6,0.016666115520282188
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,1,0.5111111111111111,0.04662257495590829
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7333333333333333,0.002212852733686067
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6,0.016666115520282188
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,4,0.5555555555555555,0.02860945767195767
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,5,0.5111111111111111,0.04662257495590829
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,6,0.6444444444444444,0.009148478835978836
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6,0.016666115520282188
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6,0.016666115520282188
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,9,0.5111111111111111,0.04662257495590829
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,0,0.7333333333333333,0.002212852733686067
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,1,0.6444444444444444,0.009148478835978836
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6888888888888888,0.00468694885361552
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,4,0.6888888888888888,0.00468694885361552
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,5,0.7333333333333333,0.002212852733686067
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,6,0.6888888888888888,0.00468694885361552
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,8,0.7333333333333333,0.002212852733686067
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,9,0.7333333333333333,0.002212852733686067
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6888888888888888,0.00468694885361552
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,1,0.5843065474681431,0.019550269092885535
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6741998624632421,0.0070583320485280866
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6292532049656926,0.011921001496914019
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,4,0.6292532049656926,0.011921001496914019
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,5,0.5843065474681431,0.019550269092885535
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,6,0.5843065474681431,0.019550269092885535
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6292532049656926,0.011921001496914019
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6888888888888888,0.00468694885361552
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,9,0.5843065474681431,0.019550269092885535
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,2,0.911111111111111,2.9761904761904762e-05
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,6,0.7333333333333333,0.002212852733686067
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,0,0.7333333333333333,0.002212852733686067
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,0,0.7640931774583409,0.002263469812035174
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,1,0.8539864924534399,0.0006436975254696865
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,3,0.8090398349558905,0.0012254240706707103
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,5,0.841126352013584,0.0008493886834182052
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,7,0.7333333333333333,0.002212852733686067
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,8,0.8090398349558905,0.0012254240706707103
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,0,0.8989331499509894,0.0003280163150135276
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,2,0.522862326927363,0.03809415806109578
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6888888888888888,0.00468694885361552
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,4,0.6888888888888888,0.00468694885361552
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6,0.016666115520282188
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,7,0.4666666666666666,0.07255015432098766
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6292532049656926,0.011921001496914019
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,0,0.9555555555555554,5.5114638447971785e-06
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,6,0.7333333333333333,0.002212852733686067
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,1,0.6,0.016666115520282188
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6888888888888888,0.00468694885361552
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,6,0.7333333333333333,0.002212852733686067
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6444444444444444,0.009148478835978836
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,0,0.35957325998039574,0.15076277502664528
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,1,0.3333333333333333,0.21637345679012346
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6444444444444444,0.009148478835978836
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,3,0.7191465199607915,0.004057136032371292
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,5,0.3026531281668172,0.23598289445748843
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,6,0.22473328748774735,0.36917141633269157
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,7,0.7956600627155523,0.0016003458153453507
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6888888888888888,0.00468694885361552
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,9,0.4222222222222222,0.10831349206349207
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,0,0.4666666666666666,0.07255015432098766
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,1,0.37777777777777777,0.1557418430335097
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,2,0.37777777777777777,0.1557418430335097
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,3,0.4666666666666666,0.07255015432098766
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,4,0.5111111111111111,0.04662257495590829
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,5,0.24444444444444444,0.38071979717813054
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,6,0.37777777777777777,0.1557418430335097
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,7,0.37777777777777777,0.1557418430335097
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,8,0.5555555555555555,0.02860945767195767
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,9,0.24444444444444444,0.38071979717813054
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,10,0,0.7333333333333333,0.002212852733686067
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7333333333333333,0.002212852733686067
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,10,4,0.6888888888888888,0.00468694885361552
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6888888888888888,0.00468694885361552
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,10,8,0.7333333333333333,0.002212852733686067
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6888888888888888,0.00468694885361552
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,10,7,0.8222222222222221,0.0003576940035273369
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,10,1,0.7333333333333333,0.002212852733686067
MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,10,3,0.7333333333333333,0.002212852733686067
MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,10,5,0.7333333333333333,0.002212852733686067
MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,10,7,0.8222222222222221,0.0003576940035273369
MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,10,9,0.7333333333333333,0.002212852733686067
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,1,0.7333333333333333,0.002212852733686067
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7333333333333333,0.002212852733686067
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,7,0.7333333333333333,0.002212852733686067
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6888888888888888,0.00468694885361552
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,9,0.7333333333333333,0.002212852733686067
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,9,0.9999999999999999,5.511463844797178e-07
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,0,0.7333333333333333,0.002212852733686067
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,1,0.6,0.016666115520282188
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6,0.016666115520282188
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6888888888888888,0.00468694885361552
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,4,0.7333333333333333,0.002212852733686067
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,5,0.7333333333333333,0.002212852733686067
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6888888888888888,0.00468694885361552
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,8,0.4222222222222222,0.10831349206349207
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6,0.016666115520282188
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,0,0.7333333333333333,0.002212852733686067
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,1,0.7333333333333333,0.002212852733686067
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6888888888888888,0.00468694885361552
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6888888888888888,0.00468694885361552
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6888888888888888,0.00468694885361552
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6888888888888888,0.00468694885361552
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,0,0.49441323247304414,0.048193488293190756
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,1,0.3146266024828463,0.2086677876982641
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,2,0.40451991747794525,0.1059975484249457
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6888888888888888,0.00468694885361552
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,4,0.6,0.016666115520282188
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6888888888888888,0.00468694885361552
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,7,0.4494665749754947,0.07248608508684644
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,8,0.5393598899705937,0.03114121059579671
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,9,0.4666666666666666,0.07255015432098766
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6888888888888888,0.00468694885361552
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,1,0.6,0.016666115520282188
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,2,0.5393598899705937,0.03114121059579671
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6292532049656926,0.011921001496914019
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,4,0.7333333333333333,0.002212852733686067
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6,0.016666115520282188
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,6,0.6444444444444444,0.009148478835978836
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,7,0.4494665749754947,0.07248608508684644
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6,0.016666115520282188
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,9,0.37777777777777777,0.1557418430335097
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6,0.016666115520282188
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,1,0.22473328748774735,0.36917141633269157
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,2,0.4666666666666666,0.07255015432098766
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6741998624632421,0.0070583320485280866
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,4,0.4666666666666666,0.07255015432098766
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,5,0.5555555555555555,0.02860945767195767
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,6,0.6444444444444444,0.009148478835978836
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,7,0.34099716973523675,0.17621399555130546
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,8,0.3333333333333333,0.21637345679012346
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6137949055234262,0.01491204965521593
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,4,0.7777777777777777,0.0009463183421516755
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,7,0.8222222222222221,0.0003576940035273369
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,0,0.8989331499509894,0.0003280163150135276
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7333333333333333,0.002212852733686067
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6,0.016666115520282188
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,4,0.6741998624632421,0.0070583320485280866
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6888888888888888,0.00468694885361552
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6444444444444444,0.009148478835978836
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,0,0.5555555555555555,0.02860945767195767
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,1,0.4666666666666666,0.07255015432098766
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6,0.016666115520282188
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6741998624632421,0.0070583320485280866
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,4,0.6,0.016666115520282188
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6444444444444444,0.009148478835978836
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,6,0.8090398349558905,0.0012254240706707103
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,7,0.4666666666666666,0.07255015432098766
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,8,0.5843065474681431,0.019550269092885535
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6,0.016666115520282188
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,10,0,0.9999999999999999,5.511463844797178e-07
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,10,1,0.9999999999999999,5.511463844797178e-07
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,10,2,0.9999999999999999,5.511463844797178e-07
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,10,3,0.9999999999999999,5.511463844797178e-07
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,10,4,0.9999999999999999,5.511463844797178e-07
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,10,5,0.9999999999999999,5.511463844797178e-07
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,10,6,0.9999999999999999,5.511463844797178e-07
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,10,7,0.9999999999999999,5.511463844797178e-07
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,10,8,0.9999999999999999,5.511463844797178e-07
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,10,9,0.9999999999999999,5.511463844797178e-07
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6888888888888888,0.00468694885361552
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6,0.016666115520282188
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,10,6,0.8989331499509894,0.0003280163150135276
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,10,8,0.8090398349558905,0.0012254240706707103
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,10,8,0.7333333333333333,0.002212852733686067
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,10,1,0.6888888888888888,0.00468694885361552
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,10,3,0.5555555555555555,0.02860945767195767
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,10,5,0.4666666666666666,0.07255015432098766
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,10,6,0.6888888888888888,0.00468694885361552
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7333333333333333,0.002212852733686067
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,10,3,0.7333333333333333,0.002212852733686067
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,10,4,0.7777777777777777,0.0009463183421516755
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,10,7,0.7333333333333333,0.002212852733686067
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,10,8,0.7333333333333333,0.002212852733686067
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,10,0,0.7333333333333333,0.002212852733686067
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6444444444444444,0.009148478835978836
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,10,3,0.7333333333333333,0.002212852733686067
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,10,4,0.6888888888888888,0.00468694885361552
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,10,6,0.8090398349558905,0.0012254240706707103
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,10,7,0.8222222222222221,0.0003576940035273369
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,3,0.9999999999999999,5.511463844797178e-07
WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,4,0.9999999999999999,5.511463844797178e-07
WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,7,0.8222222222222221,0.0003576940035273369
WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,0,0.7333333333333333,0.002212852733686067
WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,1,0.7333333333333333,0.002212852733686067
WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7333333333333333,0.002212852733686067
WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,8,0.7333333333333333,0.002212852733686067
WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6444444444444444,0.009148478835978836
WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,1,0.6888888888888888,0.00468694885361552
WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6888888888888888,0.00468694885361552
WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,4,0.7777777777777777,0.0009463183421516755
WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6888888888888888,0.00468694885361552
WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6,0.016666115520282188
WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6888888888888888,0.00468694885361552
WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6444444444444444,0.009148478835978836
WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,0,0.7333333333333333,0.002212852733686067
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6888888888888888,0.00468694885361552
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,8,0.7333333333333333,0.002212852733686067
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6888888888888888,0.00468694885361552
WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,10,7,0.8222222222222221,0.0003576940035273369
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,3,0.3333333333333333,0.21637345679012346
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,4,0.5555555555555555,0.02860945767195767
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,6,0.6888888888888888,0.00468694885361552
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,9,0.6,0.016666115520282188
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,0,0.7640931774583409,0.002263469812035174
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,2,0.6,0.016666115520282188
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,3,0.40451991747794525,0.1059975484249457
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,4,0.7640931774583409,0.002263469812035174
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,5,0.6444444444444444,0.009148478835978836
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,6,0.7191465199607915,0.004057136032371292
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,8,0.5555555555555555,0.02860945767195767
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,9,0.4494665749754947,0.07248608508684644
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,0,0.6,0.016666115520282188
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,1,0.4666666666666666,0.07255015432098766
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,2,0.6888888888888888,0.00468694885361552
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,3,0.37777777777777777,0.1557418430335097
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,4,0.4666666666666666,0.07255015432098766
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,5,0.7333333333333333,0.002212852733686067
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,6,0.6,0.016666115520282188
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,7,0.8222222222222221,0.0003576940035273369
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,9,0.6888888888888888,0.00468694885361552
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,0,0.5843065474681431,0.019550269092885535
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,2,0.5843065474681431,0.019550269092885535
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,3,0.3146266024828463,0.2086677876982641
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,4,0.6444444444444444,0.009148478835978836
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,5,0.6444444444444444,0.009148478835978836
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,6,0.4666666666666666,0.07255015432098766
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,7,0.6888888888888888,0.00468694885361552
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,8,0.6292532049656926,0.011921001496914019
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,9,0.3333333333333333,0.21637345679012346
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,3,0.6,0.016666115520282188
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,4,0.7777777777777777,0.0009463183421516755
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,5,0.6888888888888888,0.00468694885361552
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,6,0.6888888888888888,0.00468694885361552
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,8,0.7333333333333333,0.002212852733686067
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,9,0.6,0.016666115520282188
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,0,0.5555555555555555,0.02860945767195767
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,2,0.5555555555555555,0.02860945767195767
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,3,0.28888888888888886,0.2912483465608466
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,4,0.6444444444444444,0.009148478835978836
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,5,0.5111111111111111,0.04662257495590829
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,6,0.28888888888888886,0.2912483465608466
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,7,0.6888888888888888,0.00468694885361552
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,8,0.5111111111111111,0.04662257495590829
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,9,0.19999999999999998,0.4843127204585538
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,0,0.7333333333333333,0.002212852733686067
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,2,0.4666666666666666,0.07255015432098766
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,3,0.37777777777777777,0.1557418430335097
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,4,0.5555555555555555,0.02860945767195767
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,5,0.6,0.016666115520282188
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,6,0.6888888888888888,0.00468694885361552
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,8,0.5111111111111111,0.04662257495590829
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,9,0.4222222222222222,0.10831349206349207
BigBench,biggen_240829.csv,aggregate,aggregate,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
BigBench,biggen_240829.csv,aggregate,aggregate,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05
BigBench,biggen_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
BigBench,biggen_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6444444444444444,0.009148478835978836
BigBench,biggen_240829.csv,aggregate,aggregate,kendall,random,10,4,0.5111111111111111,0.04662257495590829
BigBench,biggen_240829.csv,aggregate,aggregate,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
BigBench,biggen_240829.csv,aggregate,aggregate,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
BigBench,biggen_240829.csv,aggregate,aggregate,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
BigBench,biggen_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6444444444444444,0.009148478835978836
BigBench,biggen_240829.csv,aggregate,aggregate,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
BigBench Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
BigBench Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05
BigBench Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
BigBench Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6741998624632421,0.0070583320485280866
BigBench Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,10,4,0.7191465199607915,0.004057136032371292
BigBench Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
BigBench Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
BigBench Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
BigBench Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
BigBench Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
BigBench Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6292532049656926,0.011921001496914019
BigBench Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,10,1,0.7640931774583409,0.002263469812035174
BigBench Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
BigBench Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,10,3,0.7640931774583409,0.002263469812035174
BigBench Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,10,4,0.5980568180967069,0.018255860587459292
BigBench Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,10,5,0.7333333333333333,0.002212852733686067
BigBench Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,10,6,0.7640931774583409,0.002263469812035174
BigBench Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,10,7,0.7191465199607915,0.004057136032371292
BigBench Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,10,8,0.7333333333333333,0.002212852733686067
BigBench Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,10,9,0.7640931774583409,0.002263469812035174
BigBench Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,0,0.7191465199607915,0.004057136032371292
BigBench Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,1,0.8989331499509894,0.0003280163150135276
BigBench Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7956600627155523,0.0016003458153453507
BigBench Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,3,0.5393598899705937,0.03114121059579671
BigBench Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,4,0.49441323247304414,0.048193488293190756
BigBench Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,5,0.7640931774583409,0.002263469812035174
BigBench Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,6,0.7640931774583409,0.002263469812035174
BigBench Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,7,0.7640931774583409,0.002263469812035174
BigBench Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,8,0.5111111111111111,0.04662257495590829
BigBench Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,9,0.7191465199607915,0.004057136032371292
BigBench Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,0,0.7640931774583409,0.002263469812035174
BigBench Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
BigBench Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
BigBench Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
BigBench Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,4,0.5111111111111111,0.04662257495590829
BigBench Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
BigBench Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
BigBench Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6444444444444444,0.009148478835978836
BigBench Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6888888888888888,0.00468694885361552
BigBench Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
BigBench Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6444444444444444,0.009148478835978836
BigBench Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,10,1,0.8539864924534399,0.0006436975254696865
BigBench Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6888888888888888,0.00468694885361552
BigBench Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6444444444444444,0.009148478835978836
BigBench Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,10,4,0.4494665749754947,0.07248608508684644
BigBench Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
BigBench Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
BigBench Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6292532049656926,0.011921001496914019
BigBench Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6,0.016666115520282188
BigBench Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
BigBench Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,10,0,0.5843065474681431,0.019550269092885535
BigBench Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,10,1,0.7333333333333333,0.002212852733686067
BigBench Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,10,2,0.5555555555555555,0.02860945767195767
BigBench Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6444444444444444,0.009148478835978836
BigBench Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,10,4,0.40451991747794525,0.1059975484249457
BigBench Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
BigBench Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,10,6,0.6444444444444444,0.009148478835978836
BigBench Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6444444444444444,0.009148478835978836
BigBench Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,10,8,0.5555555555555555,0.02860945767195767
BigBench Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,10,9,0.8090398349558905,0.0012254240706707103
BigBench Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6888888888888888,0.00468694885361552
BigBench Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05
BigBench Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7191465199607915,0.004057136032371292
BigBench Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,10,3,0.5555555555555555,0.02860945767195767
BigBench Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,10,4,0.5111111111111111,0.04662257495590829
BigBench Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,10,5,0.7333333333333333,0.002212852733686067
BigBench Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,10,6,0.6888888888888888,0.00468694885361552
BigBench Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
BigBench Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6741998624632421,0.0070583320485280866
BigBench Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
BigBench Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6292532049656926,0.011921001496914019
BigBench Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,10,1,0.8090398349558905,0.0012254240706707103
BigBench Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
BigBench Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6,0.016666115520282188
BigBench Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,10,4,0.3333333333333333,0.21637345679012346
BigBench Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
BigBench Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
BigBench Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6,0.016666115520282188
BigBench Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,10,8,0.5555555555555555,0.02860945767195767
BigBench Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6888888888888888,0.00468694885361552
BigBench Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,10,0,0.5555555555555555,0.02860945767195767
BigBench Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05
BigBench Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6444444444444444,0.009148478835978836
BigBench Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,10,3,0.9888264649460883,7.772240795323086e-05
BigBench Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,10,4,0.8539864924534399,0.0006436975254696865
BigBench Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,10,5,0.9888264649460883,7.772240795323086e-05
BigBench Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
BigBench Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,10,7,0.7333333333333333,0.002212852733686067
BigBench Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6444444444444444,0.009148478835978836
BigBench Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,10,9,0.4666666666666666,0.07255015432098766
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,10,0,0.9999999999999999,5.511463844797178e-07
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,10,1,0.9999999999999999,5.511463844797178e-07
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,10,2,0.911111111111111,2.9761904761904762e-05
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,10,3,0.9999999999999999,5.511463844797178e-07
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,10,4,0.9999999999999999,5.511463844797178e-07
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,10,5,0.9999999999999999,5.511463844797178e-07
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,10,6,0.9999999999999999,5.511463844797178e-07
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,10,7,0.9555555555555554,5.5114638447971785e-06
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,10,8,0.9999999999999999,5.511463844797178e-07
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,10,9,0.9999999999999999,5.511463844797178e-07
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,1,0.6888888888888888,0.00468694885361552
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,4,0.8865926413116155,0.000437257592706733
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,5,0.7360699299651778,0.0036714498212758067
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,6,0.7956600627155523,0.0016003458153453507
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,7,0.7640931774583409,0.002263469812035174
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,8,0.8539864924534399,0.0006436975254696865
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,9,0.7333333333333333,0.002212852733686067
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,0,0.8090398349558905,0.0012254240706707103
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,3,0.8090398349558905,0.0012254240706707103
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,4,0.9999999999999999,5.511463844797178e-07
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,5,0.6888888888888888,0.00468694885361552
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,9,0.9775252199076787,0.00010567442661664933
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,0,0.9555555555555554,5.5114638447971785e-06
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,2,0.911111111111111,2.9761904761904762e-05
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,6,0.7333333333333333,0.002212852733686067
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,8,0.9555555555555554,5.5114638447971785e-06
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,1,0.6444444444444444,0.009148478835978836
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,2,0.7333333333333333,0.002212852733686067
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,4,0.6888888888888888,0.00468694885361552
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,5,0.8539864924534399,0.0006436975254696865
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,7,0.8222222222222221,0.0003576940035273369
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,9,0.6444444444444444,0.009148478835978836
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,8,0.9555555555555554,5.5114638447971785e-06
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,4,0.7333333333333333,0.002212852733686067
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,5,0.6888888888888888,0.00468694885361552
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,9,0.8090398349558905,0.0012254240706707103
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,10,0,0.6,0.016666115520282188
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,10,1,0.5555555555555555,0.02860945767195767
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,10,2,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,10,3,0.6,0.016666115520282188
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,10,5,0.6,0.016666115520282188
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,10,6,0.6,0.016666115520282188
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,10,7,0.6,0.016666115520282188
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,10,8,0.6,0.016666115520282188
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,10,9,0.6,0.016666115520282188
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,0,0.22473328748774735,0.36917141633269157
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,1,0.15555555555555553,0.6006536596119929
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,2,0.3146266024828463,0.2086677876982641
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,3,0.22473328748774735,0.36917141633269157
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,4,0.3146266024828463,0.2086677876982641
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,5,0.15555555555555553,0.6006536596119929
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,6,0.3146266024828463,0.2086677876982641
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,7,0.22473328748774735,0.36917141633269157
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,8,0.22473328748774735,0.36917141633269157
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,9,0.15555555555555553,0.6006536596119929
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,0,0.3333333333333333,0.21637345679012346
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,1,0.19999999999999998,0.4843127204585538
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,2,0.4222222222222222,0.10831349206349207
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,3,0.3333333333333333,0.21637345679012346
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,4,0.4222222222222222,0.10831349206349207
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,5,0.19999999999999998,0.4843127204585538
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,6,0.4222222222222222,0.10831349206349207
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,7,0.3333333333333333,0.21637345679012346
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,8,0.3333333333333333,0.21637345679012346
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,9,0.19999999999999998,0.4843127204585538
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,0,0.6,0.016666115520282188
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,1,0.4222222222222222,0.10831349206349207
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,3,0.5111111111111111,0.04662257495590829
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,4,0.6,0.016666115520282188
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,5,0.4666666666666666,0.07255015432098766
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,6,0.6444444444444444,0.009148478835978836
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,7,0.5111111111111111,0.04662257495590829
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,8,0.6,0.016666115520282188
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,9,0.4666666666666666,0.07255015432098766
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,7,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,0,0.7191465199607915,0.004057136032371292
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,1,0.6,0.016666115520282188
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,2,0.6292532049656926,0.011921001496914019
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,3,0.5393598899705937,0.03114121059579671
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,4,0.6292532049656926,0.011921001496914019
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,5,0.6,0.016666115520282188
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,6,0.6292532049656926,0.011921001496914019
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,7,0.5393598899705937,0.03114121059579671
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,8,0.7191465199607915,0.004057136032371292
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,9,0.6,0.016666115520282188
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,0,0.4222222222222222,0.10831349206349207
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,1,0.4222222222222222,0.10831349206349207
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,2,0.4222222222222222,0.10831349206349207
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,3,0.37777777777777777,0.1557418430335097
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,4,0.4666666666666666,0.07255015432098766
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,5,0.4666666666666666,0.07255015432098766
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,6,0.28888888888888886,0.2912483465608466
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,7,0.37777777777777777,0.1557418430335097
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,8,0.4222222222222222,0.10831349206349207
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,9,0.4666666666666666,0.07255015432098766
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,0,0.6,0.016666115520282188
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,1,0.5111111111111111,0.04662257495590829
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,3,0.6,0.016666115520282188
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,4,0.5555555555555555,0.02860945767195767
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,5,0.5111111111111111,0.04662257495590829
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,6,0.6444444444444444,0.009148478835978836
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,7,0.6,0.016666115520282188
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,8,0.6,0.016666115520282188
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,9,0.5111111111111111,0.04662257495590829
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,1,0.6444444444444444,0.009148478835978836
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,2,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,4,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,1,0.5843065474681431,0.019550269092885535
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,2,0.6741998624632421,0.0070583320485280866
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,3,0.6292532049656926,0.011921001496914019
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,4,0.6292532049656926,0.011921001496914019
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,5,0.5843065474681431,0.019550269092885535
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,6,0.5843065474681431,0.019550269092885535
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,7,0.6292532049656926,0.011921001496914019
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,9,0.5843065474681431,0.019550269092885535
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.7640931774583409,0.002263469812035174
aggregate,aggregate,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.8539864924534399,0.0006436975254696865
aggregate,aggregate,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.8090398349558905,0.0012254240706707103
aggregate,aggregate,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.841126352013584,0.0008493886834182052
aggregate,aggregate,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.7333333333333333,0.002212852733686067
aggregate,aggregate,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.8090398349558905,0.0012254240706707103
aggregate,aggregate,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.8989331499509894,0.0003280163150135276
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.522862326927363,0.03809415806109578
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.6,0.016666115520282188
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.4666666666666666,0.07255015432098766
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.6292532049656926,0.011921001496914019
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.6,0.016666115520282188
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.35957325998039574,0.15076277502664528
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.3333333333333333,0.21637345679012346
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.7191465199607915,0.004057136032371292
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.3026531281668172,0.23598289445748843
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.22473328748774735,0.36917141633269157
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.7956600627155523,0.0016003458153453507
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.4222222222222222,0.10831349206349207
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.4666666666666666,0.07255015432098766
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.37777777777777777,0.1557418430335097
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.37777777777777777,0.1557418430335097
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.4666666666666666,0.07255015432098766
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.5111111111111111,0.04662257495590829
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.24444444444444444,0.38071979717813054
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.37777777777777777,0.1557418430335097
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.37777777777777777,0.1557418430335097
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.5555555555555555,0.02860945767195767
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.24444444444444444,0.38071979717813054
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,4,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,5,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,10,7,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067
aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,3,0.7333333333333333,0.002212852733686067
aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067
aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,7,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,10,7,0.7333333333333333,0.002212852733686067
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,10,9,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,1,0.6,0.016666115520282188
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,2,0.6,0.016666115520282188
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,8,0.4222222222222222,0.10831349206349207
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,9,0.6,0.016666115520282188
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,10,2,0.6888888888888888,0.00468694885361552
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,10,0,0.49441323247304414,0.048193488293190756
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,10,1,0.3146266024828463,0.2086677876982641
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,10,2,0.40451991747794525,0.1059975484249457
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,10,4,0.6,0.016666115520282188
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,10,5,0.6888888888888888,0.00468694885361552
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,10,7,0.4494665749754947,0.07248608508684644
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,10,8,0.5393598899705937,0.03114121059579671
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,10,9,0.4666666666666666,0.07255015432098766
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,1,0.6,0.016666115520282188
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,2,0.5393598899705937,0.03114121059579671
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,3,0.6292532049656926,0.011921001496914019
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,5,0.6,0.016666115520282188
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,6,0.6444444444444444,0.009148478835978836
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,7,0.4494665749754947,0.07248608508684644
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,8,0.6,0.016666115520282188
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,9,0.37777777777777777,0.1557418430335097
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,0,0.6,0.016666115520282188
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,1,0.22473328748774735,0.36917141633269157
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,2,0.4666666666666666,0.07255015432098766
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,3,0.6741998624632421,0.0070583320485280866
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,4,0.4666666666666666,0.07255015432098766
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,5,0.5555555555555555,0.02860945767195767
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,6,0.6444444444444444,0.009148478835978836
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,7,0.34099716973523675,0.17621399555130546
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,8,0.3333333333333333,0.21637345679012346
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,9,0.6137949055234262,0.01491204965521593
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,4,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,7,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,0,0.8989331499509894,0.0003280163150135276
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,3,0.6,0.016666115520282188
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,4,0.6741998624632421,0.0070583320485280866
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,8,0.6444444444444444,0.009148478835978836
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,0,0.5555555555555555,0.02860945767195767
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,1,0.4666666666666666,0.07255015432098766
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,2,0.6,0.016666115520282188
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,3,0.6741998624632421,0.0070583320485280866
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,4,0.6,0.016666115520282188
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,5,0.6444444444444444,0.009148478835978836
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,6,0.8090398349558905,0.0012254240706707103
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,7,0.4666666666666666,0.07255015432098766
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,8,0.5843065474681431,0.019550269092885535
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,9,0.6,0.016666115520282188
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,10,0,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,10,1,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,10,2,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,10,3,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,10,4,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,10,5,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,10,6,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,10,7,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,10,8,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,10,9,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,5,0.6,0.016666115520282188
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,6,0.8989331499509894,0.0003280163150135276
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,8,0.8090398349558905,0.0012254240706707103
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,3,0.5555555555555555,0.02860945767195767
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,5,0.4666666666666666,0.07255015432098766
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,10,3,0.7333333333333333,0.002212852733686067
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,10,4,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,10,7,0.7333333333333333,0.002212852733686067
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,3,0.7333333333333333,0.002212852733686067
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,4,0.6888888888888888,0.00468694885361552
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,6,0.8090398349558905,0.0012254240706707103
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,7,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,3,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,4,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,7,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067
aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067
aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067
aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067
aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836
aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552
aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,10,2,0.6888888888888888,0.00468694885361552
aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,10,4,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,10,5,0.6888888888888888,0.00468694885361552
aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,10,8,0.6,0.016666115520282188
aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,2,0.6888888888888888,0.00468694885361552
aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836
aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067
aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,2,0.6888888888888888,0.00468694885361552
aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067
aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,10,2,0.6888888888888888,0.00468694885361552
aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,10,7,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.3333333333333333,0.21637345679012346
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.5555555555555555,0.02860945767195767
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.6,0.016666115520282188
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.7640931774583409,0.002263469812035174
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.6,0.016666115520282188
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.40451991747794525,0.1059975484249457
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.7640931774583409,0.002263469812035174
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.6444444444444444,0.009148478835978836
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.7191465199607915,0.004057136032371292
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.5555555555555555,0.02860945767195767
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.4494665749754947,0.07248608508684644
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.6,0.016666115520282188
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.4666666666666666,0.07255015432098766
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.37777777777777777,0.1557418430335097
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.4666666666666666,0.07255015432098766
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.6,0.016666115520282188
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.5843065474681431,0.019550269092885535
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.5843065474681431,0.019550269092885535
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.3146266024828463,0.2086677876982641
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.6444444444444444,0.009148478835978836
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.4666666666666666,0.07255015432098766
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.6292532049656926,0.011921001496914019
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.3333333333333333,0.21637345679012346
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.6,0.016666115520282188
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.6,0.016666115520282188
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.5555555555555555,0.02860945767195767
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.5555555555555555,0.02860945767195767
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.28888888888888886,0.2912483465608466
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.5111111111111111,0.04662257495590829
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.28888888888888886,0.2912483465608466
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.5111111111111111,0.04662257495590829
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.19999999999999998,0.4843127204585538
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.4666666666666666,0.07255015432098766
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.37777777777777777,0.1557418430335097
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.5555555555555555,0.02860945767195767
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.6,0.016666115520282188
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.5111111111111111,0.04662257495590829
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.4222222222222222,0.10831349206349207
aggregate,aggregate,BigBench,biggen_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,BigBench,biggen_240829.csv,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,BigBench,biggen_240829.csv,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,BigBench,biggen_240829.csv,kendall,random,10,3,0.6444444444444444,0.009148478835978836
aggregate,aggregate,BigBench,biggen_240829.csv,kendall,random,10,4,0.5111111111111111,0.04662257495590829
aggregate,aggregate,BigBench,biggen_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,BigBench,biggen_240829.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,BigBench,biggen_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,BigBench,biggen_240829.csv,kendall,random,10,8,0.6444444444444444,0.009148478835978836
aggregate,aggregate,BigBench,biggen_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,BigBench Grounding,biggen_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,BigBench Grounding,biggen_240829.csv,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,BigBench Grounding,biggen_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,BigBench Grounding,biggen_240829.csv,kendall,random,10,3,0.6741998624632421,0.0070583320485280866
aggregate,aggregate,BigBench Grounding,biggen_240829.csv,kendall,random,10,4,0.7191465199607915,0.004057136032371292
aggregate,aggregate,BigBench Grounding,biggen_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,BigBench Grounding,biggen_240829.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,BigBench Grounding,biggen_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,BigBench Grounding,biggen_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,BigBench Grounding,biggen_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,0,0.6292532049656926,0.011921001496914019
aggregate,aggregate,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,1,0.7640931774583409,0.002263469812035174
aggregate,aggregate,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,3,0.7640931774583409,0.002263469812035174
aggregate,aggregate,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,4,0.5980568180967069,0.018255860587459292
aggregate,aggregate,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067
aggregate,aggregate,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,6,0.7640931774583409,0.002263469812035174
aggregate,aggregate,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,7,0.7191465199607915,0.004057136032371292
aggregate,aggregate,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067
aggregate,aggregate,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,9,0.7640931774583409,0.002263469812035174
aggregate,aggregate,BigBench Planning,biggen_240829.csv,kendall,random,10,0,0.7191465199607915,0.004057136032371292
aggregate,aggregate,BigBench Planning,biggen_240829.csv,kendall,random,10,1,0.8989331499509894,0.0003280163150135276
aggregate,aggregate,BigBench Planning,biggen_240829.csv,kendall,random,10,2,0.7956600627155523,0.0016003458153453507
aggregate,aggregate,BigBench Planning,biggen_240829.csv,kendall,random,10,3,0.5393598899705937,0.03114121059579671
aggregate,aggregate,BigBench Planning,biggen_240829.csv,kendall,random,10,4,0.49441323247304414,0.048193488293190756
aggregate,aggregate,BigBench Planning,biggen_240829.csv,kendall,random,10,5,0.7640931774583409,0.002263469812035174
aggregate,aggregate,BigBench Planning,biggen_240829.csv,kendall,random,10,6,0.7640931774583409,0.002263469812035174
aggregate,aggregate,BigBench Planning,biggen_240829.csv,kendall,random,10,7,0.7640931774583409,0.002263469812035174
aggregate,aggregate,BigBench Planning,biggen_240829.csv,kendall,random,10,8,0.5111111111111111,0.04662257495590829
aggregate,aggregate,BigBench Planning,biggen_240829.csv,kendall,random,10,9,0.7191465199607915,0.004057136032371292
aggregate,aggregate,BigBench Reasoning,biggen_240829.csv,kendall,random,10,0,0.7640931774583409,0.002263469812035174
aggregate,aggregate,BigBench Reasoning,biggen_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,BigBench Reasoning,biggen_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,BigBench Reasoning,biggen_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,BigBench Reasoning,biggen_240829.csv,kendall,random,10,4,0.5111111111111111,0.04662257495590829
aggregate,aggregate,BigBench Reasoning,biggen_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,BigBench Reasoning,biggen_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,BigBench Reasoning,biggen_240829.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836
aggregate,aggregate,BigBench Reasoning,biggen_240829.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552
aggregate,aggregate,BigBench Reasoning,biggen_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,BigBench Refinement,biggen_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836
aggregate,aggregate,BigBench Refinement,biggen_240829.csv,kendall,random,10,1,0.8539864924534399,0.0006436975254696865
aggregate,aggregate,BigBench Refinement,biggen_240829.csv,kendall,random,10,2,0.6888888888888888,0.00468694885361552
aggregate,aggregate,BigBench Refinement,biggen_240829.csv,kendall,random,10,3,0.6444444444444444,0.009148478835978836
aggregate,aggregate,BigBench Refinement,biggen_240829.csv,kendall,random,10,4,0.4494665749754947,0.07248608508684644
aggregate,aggregate,BigBench Refinement,biggen_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,BigBench Refinement,biggen_240829.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,BigBench Refinement,biggen_240829.csv,kendall,random,10,7,0.6292532049656926,0.011921001496914019
aggregate,aggregate,BigBench Refinement,biggen_240829.csv,kendall,random,10,8,0.6,0.016666115520282188
aggregate,aggregate,BigBench Refinement,biggen_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,BigBench Safety,biggen_240829.csv,kendall,random,10,0,0.5843065474681431,0.019550269092885535
aggregate,aggregate,BigBench Safety,biggen_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067
aggregate,aggregate,BigBench Safety,biggen_240829.csv,kendall,random,10,2,0.5555555555555555,0.02860945767195767
aggregate,aggregate,BigBench Safety,biggen_240829.csv,kendall,random,10,3,0.6444444444444444,0.009148478835978836
aggregate,aggregate,BigBench Safety,biggen_240829.csv,kendall,random,10,4,0.40451991747794525,0.1059975484249457
aggregate,aggregate,BigBench Safety,biggen_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,BigBench Safety,biggen_240829.csv,kendall,random,10,6,0.6444444444444444,0.009148478835978836
aggregate,aggregate,BigBench Safety,biggen_240829.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836
aggregate,aggregate,BigBench Safety,biggen_240829.csv,kendall,random,10,8,0.5555555555555555,0.02860945767195767
aggregate,aggregate,BigBench Safety,biggen_240829.csv,kendall,random,10,9,0.8090398349558905,0.0012254240706707103
aggregate,aggregate,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552
aggregate,aggregate,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,2,0.7191465199607915,0.004057136032371292
aggregate,aggregate,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,3,0.5555555555555555,0.02860945767195767
aggregate,aggregate,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,4,0.5111111111111111,0.04662257495590829
aggregate,aggregate,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067
aggregate,aggregate,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552
aggregate,aggregate,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,8,0.6741998624632421,0.0070583320485280866
aggregate,aggregate,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,0,0.6292532049656926,0.011921001496914019
aggregate,aggregate,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,1,0.8090398349558905,0.0012254240706707103
aggregate,aggregate,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,3,0.6,0.016666115520282188
aggregate,aggregate,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,4,0.3333333333333333,0.21637345679012346
aggregate,aggregate,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,7,0.6,0.016666115520282188
aggregate,aggregate,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,8,0.5555555555555555,0.02860945767195767
aggregate,aggregate,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552
aggregate,aggregate,BigBench Multilingual,biggen_240829.csv,kendall,random,10,0,0.5555555555555555,0.02860945767195767
aggregate,aggregate,BigBench Multilingual,biggen_240829.csv,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,BigBench Multilingual,biggen_240829.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836
aggregate,aggregate,BigBench Multilingual,biggen_240829.csv,kendall,random,10,3,0.9888264649460883,7.772240795323086e-05
aggregate,aggregate,BigBench Multilingual,biggen_240829.csv,kendall,random,10,4,0.8539864924534399,0.0006436975254696865
aggregate,aggregate,BigBench Multilingual,biggen_240829.csv,kendall,random,10,5,0.9888264649460883,7.772240795323086e-05
aggregate,aggregate,BigBench Multilingual,biggen_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,BigBench Multilingual,biggen_240829.csv,kendall,random,10,7,0.7333333333333333,0.002212852733686067
aggregate,aggregate,BigBench Multilingual,biggen_240829.csv,kendall,random,10,8,0.6444444444444444,0.009148478835978836
aggregate,aggregate,BigBench Multilingual,biggen_240829.csv,kendall,random,10,9,0.4666666666666666,0.07255015432098766
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,10,0,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,10,1,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,10,2,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,10,3,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,10,4,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,10,5,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,10,6,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,10,7,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,10,8,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,10,9,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,4,0.8865926413116155,0.000437257592706733
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,5,0.7360699299651778,0.0036714498212758067
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,6,0.7956600627155523,0.0016003458153453507
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,7,0.7640931774583409,0.002263469812035174
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,8,0.8539864924534399,0.0006436975254696865
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,0,0.8090398349558905,0.0012254240706707103
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,3,0.8090398349558905,0.0012254240706707103
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,4,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,5,0.6888888888888888,0.00468694885361552
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,9,0.9775252199076787,0.00010567442661664933
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,0,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,2,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,8,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,1,0.6444444444444444,0.009148478835978836
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,4,0.6888888888888888,0.00468694885361552
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,5,0.8539864924534399,0.0006436975254696865
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,7,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,10,8,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,5,0.6888888888888888,0.00468694885361552
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,9,0.8090398349558905,0.0012254240706707103