benchbench / cache /agreements_cache_bffcfd24eb4a8fe1f6c8ac8a0c8c21d6.csv
Yotam-Perlitz
revise cache
292d764
raw
history blame
171 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,10,0,0.9999999999999999,5.511463844797178e-07
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,1,0.9999999999999999,5.511463844797178e-07
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,2,0.9999999999999999,5.511463844797178e-07
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,3,0.9999999999999999,5.511463844797178e-07
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,4,0.9999999999999999,5.511463844797178e-07
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,5,0.9999999999999999,5.511463844797178e-07
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,6,0.9999999999999999,5.511463844797178e-07
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,7,0.9999999999999999,5.511463844797178e-07
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,8,0.9999999999999999,5.511463844797178e-07
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,9,0.9999999999999999,5.511463844797178e-07
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,0,0.35957325998039574,0.15076277502664528
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,1,0.6292532049656926,0.011921001496914019
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,2,0.06666666666666667,0.8618005952380953
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,3,0.15555555555555553,0.6006536596119929
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,4,0.1111111111111111,0.7274895282186948
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,5,0.28888888888888886,0.2912483465608466
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,6,0.5555555555555555,0.02860945767195767
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,10,8,0.4666666666666666,0.07255015432098766
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6444444444444444,0.009148478835978836
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,0,0.26967994498529685,0.2811980995641792
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,1,0.5555555555555555,0.02860945767195767
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,2,0.3333333333333333,0.21637345679012346
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,3,0.37777777777777777,0.1557418430335097
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,4,0.37777777777777777,0.1557418430335097
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,5,0.35957325998039574,0.15076277502664528
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,6,0.28888888888888886,0.2912483465608466
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,7,0.4222222222222222,0.10831349206349207
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,8,0.5555555555555555,0.02860945767195767
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,0,0.7333333333333333,0.002212852733686067
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,1,0.28888888888888886,0.2912483465608466
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,2,0.37777777777777777,0.1557418430335097
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,3,0.28888888888888886,0.2912483465608466
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,4,0.19999999999999998,0.4843127204585538
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,10,7,0.4666666666666666,0.07255015432098766
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,10,9,0.6888888888888888,0.00468694885361552
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,1,0.7333333333333333,0.002212852733686067
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,10,3,0.8222222222222221,0.0003576940035273369
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,4,0.6444444444444444,0.009148478835978836
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6592611948214576,0.008926875535053643
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,7,0.5843065474681431,0.019550269092885535
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,9,0.8539864924534399,0.0006436975254696865
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6888888888888888,0.00468694885361552
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,4,0.6444444444444444,0.009148478835978836
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,10,7,0.5843065474681431,0.019550269092885535
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6888888888888888,0.00468694885361552
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6444444444444444,0.009148478835978836
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,4,0.6,0.016666115520282188
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6444444444444444,0.009148478835978836
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,6,0.8090398349558905,0.0012254240706707103
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6444444444444444,0.009148478835978836
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,0,0.5555555555555555,0.02860945767195767
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,1,0.6,0.016666115520282188
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6292532049656925,0.011921001496914019
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6444444444444444,0.009148478835978836
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,4,0.8989331499509894,0.0003280163150135276
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,6,0.6444444444444444,0.009148478835978836
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,7,0.7191465199607915,0.004057136032371292
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,8,0.7333333333333333,0.002212852733686067
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
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,10,3,0.6888888888888888,0.00468694885361552
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,4,0.7191465199607915,0.004057136032371292
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,5,0.5555555555555555,0.02860945767195767
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,7,0.5111111111111111,0.04662257495590829
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,1,0.8090398349558905,0.0012254240706707103
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,3,0.7640931774583409,0.002263469812035174
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,4,0.6444444444444444,0.009148478835978836
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,7,0.5393598899705937,0.03114121059579671
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,0,0.5555555555555555,0.02860945767195767
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,1,0.5111111111111111,0.04662257495590829
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,3,0.49441323247304414,0.048193488293190756
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,4,0.7191465199607915,0.004057136032371292
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6888888888888888,0.00468694885361552
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,6,0.7333333333333333,0.002212852733686067
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6444444444444444,0.009148478835978836
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6,0.016666115520282188
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,1,0.4666666666666666,0.07255015432098766
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6,0.016666115520282188
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,4,0.6,0.016666115520282188
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,5,0.5111111111111111,0.04662257495590829
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,6,0.6,0.016666115520282188
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,10,8,0.5555555555555555,0.02860945767195767
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,9,0.5111111111111111,0.04662257495590829
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,10,1,0.4666666666666666,0.07255015432098766
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6888888888888888,0.00468694885361552
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,4,0.7777777777777777,0.0009463183421516755
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6444444444444444,0.009148478835978836
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,6,0.6,0.016666115520282188
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,8,0.7333333333333333,0.002212852733686067
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6444444444444444,0.009148478835978836
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,0,0.7191465199607915,0.004057136032371292
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,1,0.5843065474681431,0.019550269092885535
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8090398349558905,0.0012254240706707103
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6888888888888888,0.00468694885361552
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,4,0.8090398349558905,0.0012254240706707103
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6741998624632421,0.0070583320485280866
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,6,0.6,0.016666115520282188
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,8,0.7501937734175208,0.0029250200956793346
HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6444444444444444,0.009148478835978836
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6,0.016666115520282188
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,1,0.6444444444444444,0.009148478835978836
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7333333333333333,0.002212852733686067
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,3,0.7333333333333333,0.002212852733686067
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,4,0.6444444444444444,0.009148478835978836
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,10,6,0.6444444444444444,0.009148478835978836
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6888888888888888,0.00468694885361552
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6888888888888888,0.00468694885361552
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6888888888888888,0.00468694885361552
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,0,-0.15555555555555553,0.6006536596119929
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,1,-0.19999999999999998,0.4843127204585538
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,2,0.06666666666666667,0.8618005952380953
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,3,0.06666666666666667,0.8618005952380953
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,4,-0.1111111111111111,0.7274895282186948
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,5,0.24444444444444444,0.38071979717813054
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,6,0.4666666666666666,0.07255015432098766
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,7,-0.19999999999999998,0.4843127204585538
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,8,-0.15555555555555553,0.6006536596119929
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,9,0.022222222222222223,1.0
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
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,10,5,0.7333333333333333,0.002212852733686067
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,10,7,0.8222222222222221,0.0003576940035273369
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,8,0.9555555555555554,5.5114638447971785e-06
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6,0.016666115520282188
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,1,0.4666666666666666,0.07255015432098766
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7191465199607915,0.004057136032371292
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,4,0.6444444444444444,0.009148478835978836
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6292532049656926,0.011921001496914019
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,7,0.7333333333333333,0.002212852733686067
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6292532049656926,0.011921001496914019
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6888888888888888,0.00468694885361552
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,0,0.37777777777777777,0.1557418430335097
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,1,0.06666666666666667,0.8618005952380953
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,2,0.5555555555555555,0.02860945767195767
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,3,0.4222222222222222,0.10831349206349207
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,4,0.4222222222222222,0.10831349206349207
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,5,0.3333333333333333,0.21637345679012346
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,6,0.24444444444444444,0.38071979717813054
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6444444444444444,0.009148478835978836
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,8,0.3333333333333333,0.21637345679012346
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,10,9,0.28888888888888886,0.2912483465608466
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,10,0,0.9555555555555554,5.5114638447971785e-06
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,10,1,0.6888888888888888,0.00468694885361552
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6888888888888888,0.00468694885361552
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,10,4,0.6,0.016666115520282188
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,10,5,0.7333333333333333,0.002212852733686067
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,10,7,0.7333333333333333,0.002212852733686067
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6444444444444444,0.009148478835978836
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,10,0,0.3595732599803958,0.15076277502664528
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,10,1,0.44946657497549475,0.07248608508684644
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,10,2,0.3333333333333333,0.21637345679012346
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,10,3,0.1797866299901979,0.47249761400068846
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,10,4,0.31462660248284624,0.2086677876982641
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,10,5,0.13483997249264842,0.590013887163346
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,10,6,0.26967994498529685,0.2811980995641792
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,10,7,0.1797866299901979,0.47249761400068846
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,10,8,0.3595732599803958,0.15076277502664528
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,10,9,0.13483997249264842,0.590013887163346
Helm Classic,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
Helm Classic,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
Helm Classic,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,2,0.911111111111111,2.9761904761904762e-05
Helm Classic,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
Helm Classic,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
Helm Classic,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,5,0.7333333333333333,0.002212852733686067
Helm Classic,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
Helm Classic,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
Helm Classic,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
Helm Classic,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
Helm BoolQ,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
Helm BoolQ,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,1,0.6444444444444444,0.009148478835978836
Helm BoolQ,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
Helm BoolQ,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,3,0.7333333333333333,0.002212852733686067
Helm BoolQ,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,4,0.7333333333333333,0.002212852733686067
Helm BoolQ,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,5,0.7333333333333333,0.002212852733686067
Helm BoolQ,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
Helm BoolQ,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
Helm BoolQ,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
Helm BoolQ,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
Helm NarrativeQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6888888888888888,0.00468694885361552
Helm NarrativeQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,1,0.4666666666666666,0.07255015432098766
Helm NarrativeQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,2,0.4222222222222222,0.10831349206349207
Helm NarrativeQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
Helm NarrativeQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,4,0.5111111111111111,0.04662257495590829
Helm NarrativeQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,5,0.4222222222222222,0.10831349206349207
Helm NarrativeQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,6,0.5555555555555555,0.02860945767195767
Helm NarrativeQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,7,0.4666666666666666,0.07255015432098766
Helm NarrativeQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,8,0.37777777777777777,0.1557418430335097
Helm NarrativeQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,9,0.7333333333333333,0.002212852733686067
Helm NaturalQuestionsClosed,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
Helm NaturalQuestionsClosed,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,1,0.6,0.016666115520282188
Helm NaturalQuestionsClosed,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7333333333333333,0.002212852733686067
Helm NaturalQuestionsClosed,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6444444444444444,0.009148478835978836
Helm NaturalQuestionsClosed,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,4,0.7777777777777777,0.0009463183421516755
Helm NaturalQuestionsClosed,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6888888888888888,0.00468694885361552
Helm NaturalQuestionsClosed,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
Helm NaturalQuestionsClosed,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6444444444444444,0.009148478835978836
Helm NaturalQuestionsClosed,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
Helm NaturalQuestionsClosed,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6888888888888888,0.00468694885361552
Helm NaturalQuestionsOpen,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6888888888888888,0.00468694885361552
Helm NaturalQuestionsOpen,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,1,0.6741998624632421,0.0070583320485280866
Helm NaturalQuestionsOpen,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6,0.016666115520282188
Helm NaturalQuestionsOpen,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6888888888888888,0.00468694885361552
Helm NaturalQuestionsOpen,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,4,0.7191465199607915,0.004057136032371292
Helm NaturalQuestionsOpen,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,5,0.49441323247304414,0.048193488293190756
Helm NaturalQuestionsOpen,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,6,0.7333333333333333,0.002212852733686067
Helm NaturalQuestionsOpen,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,7,0.7191465199607915,0.004057136032371292
Helm NaturalQuestionsOpen,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6741998624632421,0.0070583320485280866
Helm NaturalQuestionsOpen,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6,0.016666115520282188
Helm QuAC,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,0,0.5555555555555555,0.02860945767195767
Helm QuAC,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,1,0.6444444444444444,0.009148478835978836
Helm QuAC,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6,0.016666115520282188
Helm QuAC,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,3,0.5555555555555555,0.02860945767195767
Helm QuAC,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,4,0.6444444444444444,0.009148478835978836
Helm QuAC,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,5,0.5555555555555555,0.02860945767195767
Helm QuAC,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,6,0.5555555555555555,0.02860945767195767
Helm QuAC,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6,0.016666115520282188
Helm QuAC,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6888888888888888,0.00468694885361552
Helm QuAC,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,9,0.5555555555555555,0.02860945767195767
Helm OpenBookQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6,0.016666115520282188
Helm OpenBookQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,1,0.5111111111111111,0.04662257495590829
Helm OpenBookQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7333333333333333,0.002212852733686067
Helm OpenBookQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,3,0.5111111111111111,0.04662257495590829
Helm OpenBookQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,4,0.6888888888888888,0.00468694885361552
Helm OpenBookQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6888888888888888,0.00468694885361552
Helm OpenBookQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,6,0.6888888888888888,0.00468694885361552
Helm OpenBookQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6,0.016666115520282188
Helm OpenBookQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6444444444444444,0.009148478835978836
Helm OpenBookQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6888888888888888,0.00468694885361552
Helm IMDB,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,0,0.7640931774583409,0.002263469812035174
Helm IMDB,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,1,0.6900655593423543,0.006458954266892998
Helm IMDB,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7360699299651778,0.0036714498212758067
Helm IMDB,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,3,0.7047274841194893,0.005187148855929351
Helm IMDB,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,4,0.7191465199607915,0.004057136032371292
Helm IMDB,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6440611887195306,0.01102341638822145
Helm IMDB,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,6,0.7501937734175208,0.0029250200956793346
Helm IMDB,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6292532049656926,0.011921001496914019
Helm IMDB,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,8,0.7191465199607915,0.004057136032371292
Helm IMDB,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6741998624632421,0.0070583320485280866
Helm CivilComments,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6,0.016666115520282188
Helm CivilComments,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,1,0.6888888888888888,0.00468694885361552
Helm CivilComments,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6444444444444444,0.009148478835978836
Helm CivilComments,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,3,0.5555555555555555,0.02860945767195767
Helm CivilComments,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,4,0.6,0.016666115520282188
Helm CivilComments,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6888888888888888,0.00468694885361552
Helm CivilComments,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,6,0.6888888888888888,0.00468694885361552
Helm CivilComments,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6444444444444444,0.009148478835978836
Helm CivilComments,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6,0.016666115520282188
Helm CivilComments,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6444444444444444,0.009148478835978836
Helm RAFT,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,0,0.49441323247304414,0.048193488293190756
Helm RAFT,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,1,0.49441323247304414,0.048193488293190756
Helm RAFT,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,2,0.49441323247304414,0.048193488293190756
Helm RAFT,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,3,0.49441323247304414,0.048193488293190756
Helm RAFT,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,4,0.49441323247304414,0.048193488293190756
Helm RAFT,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,5,0.49441323247304414,0.048193488293190756
Helm RAFT,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,6,0.49441323247304414,0.048193488293190756
Helm RAFT,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,7,0.49441323247304414,0.048193488293190756
Helm RAFT,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,8,0.49441323247304414,0.048193488293190756
Helm RAFT,helm_classic_240829.csv,aggregate,aggregate,kendall,random,10,9,0.49441323247304414,0.048193488293190756
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,4,0.9999999999999999,5.511463844797178e-07
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6888888888888888,0.00468694885361552
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,6,0.9999999999999999,5.511463844797178e-07
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6888888888888888,0.00468694885361552
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6888888888888888,0.00468694885361552
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,1,0.6888888888888888,0.00468694885361552
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,10,4,0.8666666666666666,0.00011518959435626102
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6444444444444444,0.009148478835978836
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,10,7,0.6,0.016666115520282188
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6888888888888888,0.00468694885361552
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,9,0.7333333333333333,0.002212852733686067
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6888888888888888,0.00468694885361552
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,1,0.6888888888888888,0.00468694885361552
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6888888888888888,0.00468694885361552
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6,0.016666115520282188
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,10,8,0.7333333333333333,0.002212852733686067
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6444444444444444,0.009148478835978836
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6888888888888888,0.00468694885361552
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,1,0.7640931774583409,0.002263469812035174
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8539864924534399,0.0006436975254696865
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,4,0.8090398349558905,0.0012254240706707103
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6888888888888888,0.00468694885361552
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,7,0.7191465199607915,0.004057136032371292
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,8,0.7191465199607915,0.004057136032371292
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,0,0.5111111111111111,0.04662257495590829
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,1,0.6,0.016666115520282188
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7333333333333333,0.002212852733686067
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,3,0.5555555555555555,0.02860945767195767
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,4,0.5555555555555555,0.02860945767195767
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6444444444444444,0.009148478835978836
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,6,0.6,0.016666115520282188
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6,0.016666115520282188
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6,0.016666115520282188
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6292532049656926,0.011921001496914019
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6,0.016666115520282188
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,1,0.6,0.016666115520282188
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7333333333333333,0.002212852733686067
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6444444444444444,0.009148478835978836
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,4,0.5843065474681431,0.019550269092885535
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,5,0.4222222222222222,0.10831349206349207
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,6,0.7640931774583409,0.002263469812035174
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6,0.016666115520282188
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,8,0.40451991747794525,0.1059975484249457
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,9,0.7501937734175208,0.0029250200956793346
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6,0.016666115520282188
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,1,0.6,0.016666115520282188
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7333333333333333,0.002212852733686067
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6444444444444444,0.009148478835978836
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,10,5,0.5111111111111111,0.04662257495590829
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,6,0.7333333333333333,0.002212852733686067
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6444444444444444,0.009148478835978836
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,8,0.5555555555555555,0.02860945767195767
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6444444444444444,0.009148478835978836
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6444444444444444,0.009148478835978836
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,1,0.7640931774583409,0.002263469812035174
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7191465199607915,0.004057136032371292
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,3,0.5555555555555555,0.02860945767195767
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,4,0.6440611887195306,0.011244704061853582
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,5,0.5555555555555555,0.02860945767195767
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,6,0.7501937734175208,0.0029250200956793346
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6292532049656926,0.011921001496914019
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,10,9,0.5843065474681431,0.019550269092885535
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,0,0.5111111111111111,0.04662257495590829
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,1,0.6,0.016666115520282188
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
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,10,5,0.5555555555555555,0.02860945767195767
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,7,0.5111111111111111,0.04662257495590829
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,8,0.5111111111111111,0.04662257495590829
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,10,9,0.7333333333333333,0.002212852733686067
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6888888888888888,0.00468694885361552
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,10,1,0.6,0.016666115520282188
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6,0.016666115520282188
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6,0.016666115520282188
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,10,4,0.5111111111111111,0.04662257495590829
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6444444444444444,0.009148478835978836
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,10,6,0.5555555555555555,0.02860945767195767
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6,0.016666115520282188
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6888888888888888,0.00468694885361552
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6444444444444444,0.009148478835978836
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,10,0,0.4666666666666666,0.07255015432098766
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,10,1,0.4494665749754947,0.07248608508684644
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,10,2,0.4494665749754947,0.07248608508684644
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,10,3,0.5393598899705937,0.03114121059579671
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,10,4,0.40451991747794525,0.1059975484249457
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,10,5,0.5393598899705937,0.03114121059579671
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,10,6,0.4494665749754947,0.07248608508684644
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,10,7,0.5393598899705937,0.03114121059579671
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,10,8,0.4666666666666666,0.07255015432098766
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,10,9,0.5393598899705937,0.03114121059579671
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6888888888888888,0.00468694885361552
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,10,1,0.6,0.016666115520282188
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,10,2,0.5555555555555555,0.02860945767195767
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6,0.016666115520282188
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,10,4,0.5111111111111111,0.04662257495590829
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6444444444444444,0.009148478835978836
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,10,6,0.5555555555555555,0.02860945767195767
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6,0.016666115520282188
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6888888888888888,0.00468694885361552
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6444444444444444,0.009148478835978836
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6888888888888888,0.00468694885361552
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,10,1,0.6,0.016666115520282188
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6,0.016666115520282188
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6,0.016666115520282188
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,10,4,0.5111111111111111,0.04662257495590829
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6,0.016666115520282188
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,10,6,0.5555555555555555,0.02860945767195767
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6,0.016666115520282188
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6888888888888888,0.00468694885361552
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6,0.016666115520282188
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,10,0,0.5111111111111111,0.04662257495590829
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,10,1,0.4222222222222222,0.10831349206349207
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,10,2,0.4666666666666666,0.07255015432098766
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,10,3,0.3333333333333333,0.21637345679012346
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,10,4,0.3333333333333333,0.21637345679012346
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,10,5,0.4222222222222222,0.10831349206349207
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,10,6,0.37777777777777777,0.1557418430335097
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,10,7,0.3333333333333333,0.21637345679012346
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,10,8,0.5111111111111111,0.04662257495590829
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,10,9,0.4222222222222222,0.10831349206349207
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6444444444444444,0.009148478835978836
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,10,1,0.6,0.016666115520282188
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6444444444444444,0.009148478835978836
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6,0.016666115520282188
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,10,4,0.5111111111111111,0.04662257495590829
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6888888888888888,0.00468694885361552
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,10,6,0.5555555555555555,0.02860945767195767
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6,0.016666115520282188
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6444444444444444,0.009148478835978836
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6888888888888888,0.00468694885361552
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,10,1,0.6888888888888888,0.00468694885361552
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6888888888888888,0.00468694885361552
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,10,3,0.6888888888888888,0.00468694885361552
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,10,4,0.6,0.016666115520282188
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,10,5,0.6888888888888888,0.00468694885361552
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,10,6,0.6444444444444444,0.009148478835978836
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6888888888888888,0.00468694885361552
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,10,8,0.7333333333333333,0.002212852733686067
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,10,9,0.6888888888888888,0.00468694885361552
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,10,0,0.3595732599803958,0.15076277502664528
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,10,1,0.44946657497549475,0.07248608508684644
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,10,2,0.3333333333333333,0.21637345679012346
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,10,3,0.1797866299901979,0.47249761400068846
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,10,4,0.31462660248284624,0.2086677876982641
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,10,5,0.13483997249264842,0.590013887163346
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,10,6,0.26967994498529685,0.2811980995641792
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,10,7,0.1797866299901979,0.47249761400068846
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,10,8,0.3595732599803958,0.15076277502664528
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,10,9,0.13483997249264842,0.590013887163346
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,10,1,0.6888888888888888,0.00468694885361552
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,3,0.6888888888888888,0.00468694885361552
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,4,0.7333333333333333,0.002212852733686067
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,7,0.9555555555555554,5.5114638447971785e-06
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,8,0.7333333333333333,0.002212852733686067
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,9,0.7333333333333333,0.002212852733686067
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,0,0.6888888888888888,0.00468694885361552
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,1,0.5111111111111111,0.04662257495590829
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,2,0.6444444444444444,0.009148478835978836
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,3,0.5555555555555555,0.02860945767195767
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,4,0.6888888888888888,0.00468694885361552
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,5,0.7333333333333333,0.002212852733686067
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,6,0.7333333333333333,0.002212852733686067
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,7,0.7333333333333333,0.002212852733686067
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,8,0.6,0.016666115520282188
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,9,0.6888888888888888,0.00468694885361552
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,3,0.6888888888888888,0.00468694885361552
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06
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,10,8,0.7333333333333333,0.002212852733686067
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,0,0.5111111111111111,0.04662257495590829
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,1,0.37777777777777777,0.1557418430335097
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,2,0.6,0.016666115520282188
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,3,0.5555555555555555,0.02860945767195767
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,4,0.6,0.016666115520282188
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,10,6,0.7333333333333333,0.002212852733686067
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,8,0.4666666666666666,0.07255015432098766
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,9,0.5111111111111111,0.04662257495590829
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,7,0.9555555555555554,5.5114638447971785e-06
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,10,9,0.8666666666666666,0.00011518959435626102
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,0,0.6888888888888888,0.00468694885361552
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,1,0.6,0.016666115520282188
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,3,0.5111111111111111,0.04662257495590829
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,4,0.6888888888888888,0.00468694885361552
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,7,0.8222222222222221,0.0003576940035273369
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,8,0.6888888888888888,0.00468694885361552
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,9,0.6,0.016666115520282188
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,0,0.6444444444444444,0.009148478835978836
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,1,0.4666666666666666,0.07255015432098766
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,2,0.5555555555555555,0.02860945767195767
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,3,0.5555555555555555,0.02860945767195767
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,5,0.6888888888888888,0.00468694885361552
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,6,0.7333333333333333,0.002212852733686067
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,7,0.6888888888888888,0.00468694885361552
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,8,0.6,0.016666115520282188
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
BigBench,biggen_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6444444444444444,0.009148478835978836
BigBench,biggen_240829.csv,aggregate,aggregate,kendall,random,10,1,0.4666666666666666,0.07255015432098766
BigBench,biggen_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
BigBench,biggen_240829.csv,aggregate,aggregate,kendall,random,10,3,0.4222222222222222,0.10831349206349207
BigBench,biggen_240829.csv,aggregate,aggregate,kendall,random,10,4,0.7333333333333333,0.002212852733686067
BigBench,biggen_240829.csv,aggregate,aggregate,kendall,random,10,5,0.4222222222222222,0.10831349206349207
BigBench,biggen_240829.csv,aggregate,aggregate,kendall,random,10,6,0.6444444444444444,0.009148478835978836
BigBench,biggen_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6,0.016666115520282188
BigBench,biggen_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6444444444444444,0.009148478835978836
BigBench,biggen_240829.csv,aggregate,aggregate,kendall,random,10,9,0.5111111111111111,0.04662257495590829
BigBench Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,10,0,0.4666666666666666,0.07255015432098766
BigBench Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,10,1,0.28888888888888886,0.2912483465608466
BigBench Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6444444444444444,0.009148478835978836
BigBench Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,10,3,0.37777777777777777,0.1557418430335097
BigBench Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,10,4,0.6888888888888888,0.00468694885361552
BigBench Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,10,5,0.4222222222222222,0.10831349206349207
BigBench Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,10,6,0.6888888888888888,0.00468694885361552
BigBench Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6444444444444444,0.009148478835978836
BigBench Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6888888888888888,0.00468694885361552
BigBench Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,10,9,0.4222222222222222,0.10831349206349207
BigBench Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6,0.016666115520282188
BigBench Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,10,1,0.37777777777777777,0.1557418430335097
BigBench Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
BigBench Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,10,3,0.24444444444444444,0.38071979717813054
BigBench Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,10,4,0.7777777777777777,0.0009463183421516755
BigBench Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,10,5,0.4222222222222222,0.10831349206349207
BigBench Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,10,6,0.6444444444444444,0.009148478835978836
BigBench Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,10,7,0.5111111111111111,0.04662257495590829
BigBench Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6888888888888888,0.00468694885361552
BigBench Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,10,9,0.5111111111111111,0.04662257495590829
BigBench Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6,0.016666115520282188
BigBench Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,1,0.37777777777777777,0.1557418430335097
BigBench Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
BigBench Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,3,0.3146266024828463,0.2086677876982641
BigBench Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,4,0.6888888888888888,0.00468694885361552
BigBench Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,5,0.4222222222222222,0.10831349206349207
BigBench Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,6,0.5843065474681431,0.019550269092885535
BigBench Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,7,0.49441323247304414,0.048193488293190756
BigBench Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6444444444444444,0.009148478835978836
BigBench Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,9,0.4666666666666666,0.07255015432098766
BigBench Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6444444444444444,0.009148478835978836
BigBench Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,1,0.4666666666666666,0.07255015432098766
BigBench Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
BigBench Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,3,0.28888888888888886,0.2912483465608466
BigBench Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,4,0.7777777777777777,0.0009463183421516755
BigBench Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,5,0.4222222222222222,0.10831349206349207
BigBench Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,6,0.6,0.016666115520282188
BigBench Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6,0.016666115520282188
BigBench Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6888888888888888,0.00468694885361552
BigBench Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,10,9,0.4222222222222222,0.10831349206349207
BigBench Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,10,0,0.6888888888888888,0.00468694885361552
BigBench Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,10,1,0.5555555555555555,0.02860945767195767
BigBench Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,10,2,0.7333333333333333,0.002212852733686067
BigBench Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,10,3,0.5111111111111111,0.04662257495590829
BigBench Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
BigBench Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,10,5,0.5111111111111111,0.04662257495590829
BigBench Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
BigBench Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,10,7,0.6,0.016666115520282188
BigBench Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,10,8,0.7333333333333333,0.002212852733686067
BigBench Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,10,9,0.4666666666666666,0.07255015432098766
BigBench Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,10,0,0.28888888888888886,0.2912483465608466
BigBench Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,10,1,0.24444444444444444,0.38071979717813054
BigBench Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,10,2,0.5111111111111111,0.04662257495590829
BigBench Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,10,3,0.24444444444444444,0.38071979717813054
BigBench Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,10,4,0.24444444444444444,0.38071979717813054
BigBench Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,10,5,0.19999999999999998,0.4843127204585538
BigBench Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,10,6,0.4666666666666666,0.07255015432098766
BigBench Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,10,7,0.3333333333333333,0.21637345679012346
BigBench Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,10,8,0.4666666666666666,0.07255015432098766
BigBench Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,10,9,0.3333333333333333,0.21637345679012346
BigBench Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,10,0,0.5111111111111111,0.04662257495590829
BigBench Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,10,1,0.3333333333333333,0.21637345679012346
BigBench Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,10,2,0.6888888888888888,0.00468694885361552
BigBench Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,10,3,0.3333333333333333,0.21637345679012346
BigBench Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,10,4,0.5555555555555555,0.02860945767195767
BigBench Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,10,5,0.3333333333333333,0.21637345679012346
BigBench Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,10,6,0.5111111111111111,0.04662257495590829
BigBench Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,10,7,0.4666666666666666,0.07255015432098766
BigBench Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,10,8,0.6,0.016666115520282188
BigBench Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,10,9,0.37777777777777777,0.1557418430335097
BigBench Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,10,0,0.5555555555555555,0.02860945767195767
BigBench Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,10,1,0.28888888888888886,0.2912483465608466
BigBench Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,10,2,0.8090398349558905,0.0012254240706707103
BigBench Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,10,3,0.35957325998039574,0.15076277502664528
BigBench Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,10,4,0.7777777777777777,0.0009463183421516755
BigBench Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,10,5,0.4494665749754947,0.07248608508684644
BigBench Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,10,6,0.6888888888888888,0.00468694885361552
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,10,8,0.6444444444444444,0.009148478835978836
BigBench Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,10,9,0.49441323247304414,0.048193488293190756
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,10,0,0.5555555555555555,0.02860945767195767
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,10,1,0.6,0.016666115520282188
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,10,2,0.6,0.016666115520282188
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,10,3,0.5111111111111111,0.04662257495590829
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,10,4,0.6444444444444444,0.009148478835978836
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,10,5,0.5555555555555555,0.02860945767195767
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,10,6,0.6888888888888888,0.00468694885361552
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,10,7,0.5111111111111111,0.04662257495590829
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,10,8,0.5555555555555555,0.02860945767195767
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,10,9,0.5555555555555555,0.02860945767195767
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,0,0.5683286162253945,0.02418521832271127
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,1,0.7501937734175208,0.0029250200956793346
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,2,0.6592611948214576,0.008926875535053643
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,3,0.522862326927363,0.03809415806109578
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,4,0.5393598899705937,0.03114121059579671
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,5,0.6137949055234262,0.01491204965521593
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,6,0.6137949055234262,0.01491204965521593
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,7,0.522862326927363,0.03809415806109578
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,8,0.5683286162253945,0.02418521832271127
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,9,0.6137949055234262,0.01491204965521593
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,0,0.5555555555555555,0.02860945767195767
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,1,0.6,0.016666115520282188
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,2,0.5555555555555555,0.02860945767195767
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,3,0.5111111111111111,0.04662257495590829
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,4,0.6,0.016666115520282188
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,5,0.5111111111111111,0.04662257495590829
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,6,0.6444444444444444,0.009148478835978836
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,7,0.5111111111111111,0.04662257495590829
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,8,0.5555555555555555,0.02860945767195767
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,9,0.5111111111111111,0.04662257495590829
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,0,0.5555555555555555,0.02860945767195767
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,1,0.6444444444444444,0.009148478835978836
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,2,0.6,0.016666115520282188
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,3,0.5111111111111111,0.04662257495590829
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,4,0.6,0.016666115520282188
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,5,0.6,0.016666115520282188
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,6,0.6888888888888888,0.00468694885361552
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,7,0.5111111111111111,0.04662257495590829
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,8,0.5555555555555555,0.02860945767195767
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,9,0.6,0.016666115520282188
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,0,0.37777777777777777,0.1557418430335097
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,1,0.4666666666666666,0.07255015432098766
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,2,0.3333333333333333,0.21637345679012346
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,3,0.3333333333333333,0.21637345679012346
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,4,0.4222222222222222,0.10831349206349207
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,5,0.4222222222222222,0.10831349206349207
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,6,0.5111111111111111,0.04662257495590829
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,7,0.3333333333333333,0.21637345679012346
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,8,0.37777777777777777,0.1557418430335097
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,9,0.4222222222222222,0.10831349206349207
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,0,0.5555555555555555,0.02860945767195767
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,1,0.5555555555555555,0.02860945767195767
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,2,0.6,0.016666115520282188
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,3,0.5111111111111111,0.04662257495590829
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,4,0.6888888888888888,0.00468694885361552
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,5,0.6,0.016666115520282188
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,6,0.6444444444444444,0.009148478835978836
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,7,0.5111111111111111,0.04662257495590829
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,8,0.5555555555555555,0.02860945767195767
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,9,0.6,0.016666115520282188
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,0,0.6444444444444444,0.009148478835978836
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,1,0.6,0.016666115520282188
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,2,0.6888888888888888,0.00468694885361552
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,3,0.6,0.016666115520282188
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,4,0.6888888888888888,0.00468694885361552
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,5,0.7333333333333333,0.002212852733686067
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,6,0.7333333333333333,0.002212852733686067
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,7,0.6,0.016666115520282188
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,8,0.6444444444444444,0.009148478835978836
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,10,9,0.7333333333333333,0.002212852733686067
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,10,0,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,10,1,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,10,2,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,10,3,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,10,4,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,10,5,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,10,6,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,10,7,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,10,8,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,10,9,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,0,0.35957325998039574,0.15076277502664528
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,1,0.6292532049656926,0.011921001496914019
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,2,0.06666666666666667,0.8618005952380953
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,3,0.15555555555555553,0.6006536596119929
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,4,0.1111111111111111,0.7274895282186948
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,5,0.28888888888888886,0.2912483465608466
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,6,0.5555555555555555,0.02860945767195767
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,10,8,0.4666666666666666,0.07255015432098766
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,0,0.26967994498529685,0.2811980995641792
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,1,0.5555555555555555,0.02860945767195767
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,2,0.3333333333333333,0.21637345679012346
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,3,0.37777777777777777,0.1557418430335097
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,4,0.37777777777777777,0.1557418430335097
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,5,0.35957325998039574,0.15076277502664528
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,6,0.28888888888888886,0.2912483465608466
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,7,0.4222222222222222,0.10831349206349207
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,8,0.5555555555555555,0.02860945767195767
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,1,0.28888888888888886,0.2912483465608466
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,2,0.37777777777777777,0.1557418430335097
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,3,0.28888888888888886,0.2912483465608466
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,4,0.19999999999999998,0.4843127204585538
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,10,7,0.4666666666666666,0.07255015432098766
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,10,9,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067
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,10,3,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,5,0.6592611948214576,0.008926875535053643
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,7,0.5843065474681431,0.019550269092885535
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,9,0.8539864924534399,0.0006436975254696865
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836
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,10,7,0.5843065474681431,0.019550269092885535
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,4,0.6,0.016666115520282188
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,5,0.6444444444444444,0.009148478835978836
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,6,0.8090398349558905,0.0012254240706707103
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,0,0.5555555555555555,0.02860945767195767
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,1,0.6,0.016666115520282188
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,2,0.6292532049656925,0.011921001496914019
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,3,0.6444444444444444,0.009148478835978836
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,4,0.8989331499509894,0.0003280163150135276
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,6,0.6444444444444444,0.009148478835978836
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,7,0.7191465199607915,0.004057136032371292
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
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,10,3,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,4,0.7191465199607915,0.004057136032371292
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,5,0.5555555555555555,0.02860945767195767
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,7,0.5111111111111111,0.04662257495590829
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,1,0.8090398349558905,0.0012254240706707103
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,3,0.7640931774583409,0.002263469812035174
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,7,0.5393598899705937,0.03114121059579671
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,0,0.5555555555555555,0.02860945767195767
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,1,0.5111111111111111,0.04662257495590829
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,3,0.49441323247304414,0.048193488293190756
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,4,0.7191465199607915,0.004057136032371292
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,5,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.6,0.016666115520282188
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.4666666666666666,0.07255015432098766
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.6,0.016666115520282188
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.6,0.016666115520282188
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.5111111111111111,0.04662257495590829
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.6,0.016666115520282188
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,10,8,0.5555555555555555,0.02860945767195767
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.5111111111111111,0.04662257495590829
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,10,1,0.4666666666666666,0.07255015432098766
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.6444444444444444,0.009148478835978836
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.6,0.016666115520282188
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836
aggregate,aggregate,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.7191465199607915,0.004057136032371292
aggregate,aggregate,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.5843065474681431,0.019550269092885535
aggregate,aggregate,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.8090398349558905,0.0012254240706707103
aggregate,aggregate,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.8090398349558905,0.0012254240706707103
aggregate,aggregate,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.6741998624632421,0.0070583320485280866
aggregate,aggregate,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.6,0.016666115520282188
aggregate,aggregate,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.7501937734175208,0.0029250200956793346
aggregate,aggregate,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.6,0.016666115520282188
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.6444444444444444,0.009148478835978836
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.7333333333333333,0.002212852733686067
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836
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,10,6,0.6444444444444444,0.009148478835978836
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,0,-0.15555555555555553,0.6006536596119929
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,1,-0.19999999999999998,0.4843127204585538
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.06666666666666667,0.8618005952380953
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.06666666666666667,0.8618005952380953
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,4,-0.1111111111111111,0.7274895282186948
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.24444444444444444,0.38071979717813054
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.4666666666666666,0.07255015432098766
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,7,-0.19999999999999998,0.4843127204585538
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,8,-0.15555555555555553,0.6006536596119929
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.022222222222222223,1.0
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
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,10,5,0.7333333333333333,0.002212852733686067
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,10,7,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.6,0.016666115520282188
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.4666666666666666,0.07255015432098766
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.7191465199607915,0.004057136032371292
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.6292532049656926,0.011921001496914019
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.7333333333333333,0.002212852733686067
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.6292532049656926,0.011921001496914019
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.37777777777777777,0.1557418430335097
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.06666666666666667,0.8618005952380953
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.5555555555555555,0.02860945767195767
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.4222222222222222,0.10831349206349207
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.4222222222222222,0.10831349206349207
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.3333333333333333,0.21637345679012346
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.24444444444444444,0.38071979717813054
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.3333333333333333,0.21637345679012346
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.28888888888888886,0.2912483465608466
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,0,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,4,0.6,0.016666115520282188
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,7,0.7333333333333333,0.002212852733686067
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,10,0,0.3595732599803958,0.15076277502664528
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,10,1,0.44946657497549475,0.07248608508684644
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,10,2,0.3333333333333333,0.21637345679012346
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,10,3,0.1797866299901979,0.47249761400068846
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,10,4,0.31462660248284624,0.2086677876982641
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,10,5,0.13483997249264842,0.590013887163346
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,10,6,0.26967994498529685,0.2811980995641792
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,10,7,0.1797866299901979,0.47249761400068846
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,10,8,0.3595732599803958,0.15076277502664528
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,10,9,0.13483997249264842,0.590013887163346
aggregate,aggregate,Helm Classic,helm_classic_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm Classic,helm_classic_240829.csv,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,Helm Classic,helm_classic_240829.csv,kendall,random,10,2,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,Helm Classic,helm_classic_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,Helm Classic,helm_classic_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm Classic,helm_classic_240829.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067
aggregate,aggregate,Helm Classic,helm_classic_240829.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,Helm Classic,helm_classic_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,Helm Classic,helm_classic_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm Classic,helm_classic_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm BoolQ,helm_classic_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,Helm BoolQ,helm_classic_240829.csv,kendall,random,10,1,0.6444444444444444,0.009148478835978836
aggregate,aggregate,Helm BoolQ,helm_classic_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm BoolQ,helm_classic_240829.csv,kendall,random,10,3,0.7333333333333333,0.002212852733686067
aggregate,aggregate,Helm BoolQ,helm_classic_240829.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067
aggregate,aggregate,Helm BoolQ,helm_classic_240829.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067
aggregate,aggregate,Helm BoolQ,helm_classic_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm BoolQ,helm_classic_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,Helm BoolQ,helm_classic_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,Helm BoolQ,helm_classic_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,Helm NarrativeQA,helm_classic_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm NarrativeQA,helm_classic_240829.csv,kendall,random,10,1,0.4666666666666666,0.07255015432098766
aggregate,aggregate,Helm NarrativeQA,helm_classic_240829.csv,kendall,random,10,2,0.4222222222222222,0.10831349206349207
aggregate,aggregate,Helm NarrativeQA,helm_classic_240829.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm NarrativeQA,helm_classic_240829.csv,kendall,random,10,4,0.5111111111111111,0.04662257495590829
aggregate,aggregate,Helm NarrativeQA,helm_classic_240829.csv,kendall,random,10,5,0.4222222222222222,0.10831349206349207
aggregate,aggregate,Helm NarrativeQA,helm_classic_240829.csv,kendall,random,10,6,0.5555555555555555,0.02860945767195767
aggregate,aggregate,Helm NarrativeQA,helm_classic_240829.csv,kendall,random,10,7,0.4666666666666666,0.07255015432098766
aggregate,aggregate,Helm NarrativeQA,helm_classic_240829.csv,kendall,random,10,8,0.37777777777777777,0.1557418430335097
aggregate,aggregate,Helm NarrativeQA,helm_classic_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067
aggregate,aggregate,Helm NaturalQuestionsClosed,helm_classic_240829.csv,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,Helm NaturalQuestionsClosed,helm_classic_240829.csv,kendall,random,10,1,0.6,0.016666115520282188
aggregate,aggregate,Helm NaturalQuestionsClosed,helm_classic_240829.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067
aggregate,aggregate,Helm NaturalQuestionsClosed,helm_classic_240829.csv,kendall,random,10,3,0.6444444444444444,0.009148478835978836
aggregate,aggregate,Helm NaturalQuestionsClosed,helm_classic_240829.csv,kendall,random,10,4,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,Helm NaturalQuestionsClosed,helm_classic_240829.csv,kendall,random,10,5,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm NaturalQuestionsClosed,helm_classic_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,Helm NaturalQuestionsClosed,helm_classic_240829.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836
aggregate,aggregate,Helm NaturalQuestionsClosed,helm_classic_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,Helm NaturalQuestionsClosed,helm_classic_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm NaturalQuestionsOpen,helm_classic_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm NaturalQuestionsOpen,helm_classic_240829.csv,kendall,random,10,1,0.6741998624632421,0.0070583320485280866
aggregate,aggregate,Helm NaturalQuestionsOpen,helm_classic_240829.csv,kendall,random,10,2,0.6,0.016666115520282188
aggregate,aggregate,Helm NaturalQuestionsOpen,helm_classic_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm NaturalQuestionsOpen,helm_classic_240829.csv,kendall,random,10,4,0.7191465199607915,0.004057136032371292
aggregate,aggregate,Helm NaturalQuestionsOpen,helm_classic_240829.csv,kendall,random,10,5,0.49441323247304414,0.048193488293190756
aggregate,aggregate,Helm NaturalQuestionsOpen,helm_classic_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067
aggregate,aggregate,Helm NaturalQuestionsOpen,helm_classic_240829.csv,kendall,random,10,7,0.7191465199607915,0.004057136032371292
aggregate,aggregate,Helm NaturalQuestionsOpen,helm_classic_240829.csv,kendall,random,10,8,0.6741998624632421,0.0070583320485280866
aggregate,aggregate,Helm NaturalQuestionsOpen,helm_classic_240829.csv,kendall,random,10,9,0.6,0.016666115520282188
aggregate,aggregate,Helm QuAC,helm_classic_240829.csv,kendall,random,10,0,0.5555555555555555,0.02860945767195767
aggregate,aggregate,Helm QuAC,helm_classic_240829.csv,kendall,random,10,1,0.6444444444444444,0.009148478835978836
aggregate,aggregate,Helm QuAC,helm_classic_240829.csv,kendall,random,10,2,0.6,0.016666115520282188
aggregate,aggregate,Helm QuAC,helm_classic_240829.csv,kendall,random,10,3,0.5555555555555555,0.02860945767195767
aggregate,aggregate,Helm QuAC,helm_classic_240829.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836
aggregate,aggregate,Helm QuAC,helm_classic_240829.csv,kendall,random,10,5,0.5555555555555555,0.02860945767195767
aggregate,aggregate,Helm QuAC,helm_classic_240829.csv,kendall,random,10,6,0.5555555555555555,0.02860945767195767
aggregate,aggregate,Helm QuAC,helm_classic_240829.csv,kendall,random,10,7,0.6,0.016666115520282188
aggregate,aggregate,Helm QuAC,helm_classic_240829.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm QuAC,helm_classic_240829.csv,kendall,random,10,9,0.5555555555555555,0.02860945767195767
aggregate,aggregate,Helm OpenBookQA,helm_classic_240829.csv,kendall,random,10,0,0.6,0.016666115520282188
aggregate,aggregate,Helm OpenBookQA,helm_classic_240829.csv,kendall,random,10,1,0.5111111111111111,0.04662257495590829
aggregate,aggregate,Helm OpenBookQA,helm_classic_240829.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067
aggregate,aggregate,Helm OpenBookQA,helm_classic_240829.csv,kendall,random,10,3,0.5111111111111111,0.04662257495590829
aggregate,aggregate,Helm OpenBookQA,helm_classic_240829.csv,kendall,random,10,4,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm OpenBookQA,helm_classic_240829.csv,kendall,random,10,5,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm OpenBookQA,helm_classic_240829.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm OpenBookQA,helm_classic_240829.csv,kendall,random,10,7,0.6,0.016666115520282188
aggregate,aggregate,Helm OpenBookQA,helm_classic_240829.csv,kendall,random,10,8,0.6444444444444444,0.009148478835978836
aggregate,aggregate,Helm OpenBookQA,helm_classic_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm IMDB,helm_classic_240829.csv,kendall,random,10,0,0.7640931774583409,0.002263469812035174
aggregate,aggregate,Helm IMDB,helm_classic_240829.csv,kendall,random,10,1,0.6900655593423543,0.006458954266892998
aggregate,aggregate,Helm IMDB,helm_classic_240829.csv,kendall,random,10,2,0.7360699299651778,0.0036714498212758067
aggregate,aggregate,Helm IMDB,helm_classic_240829.csv,kendall,random,10,3,0.7047274841194893,0.005187148855929351
aggregate,aggregate,Helm IMDB,helm_classic_240829.csv,kendall,random,10,4,0.7191465199607915,0.004057136032371292
aggregate,aggregate,Helm IMDB,helm_classic_240829.csv,kendall,random,10,5,0.6440611887195306,0.01102341638822145
aggregate,aggregate,Helm IMDB,helm_classic_240829.csv,kendall,random,10,6,0.7501937734175208,0.0029250200956793346
aggregate,aggregate,Helm IMDB,helm_classic_240829.csv,kendall,random,10,7,0.6292532049656926,0.011921001496914019
aggregate,aggregate,Helm IMDB,helm_classic_240829.csv,kendall,random,10,8,0.7191465199607915,0.004057136032371292
aggregate,aggregate,Helm IMDB,helm_classic_240829.csv,kendall,random,10,9,0.6741998624632421,0.0070583320485280866
aggregate,aggregate,Helm CivilComments,helm_classic_240829.csv,kendall,random,10,0,0.6,0.016666115520282188
aggregate,aggregate,Helm CivilComments,helm_classic_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm CivilComments,helm_classic_240829.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836
aggregate,aggregate,Helm CivilComments,helm_classic_240829.csv,kendall,random,10,3,0.5555555555555555,0.02860945767195767
aggregate,aggregate,Helm CivilComments,helm_classic_240829.csv,kendall,random,10,4,0.6,0.016666115520282188
aggregate,aggregate,Helm CivilComments,helm_classic_240829.csv,kendall,random,10,5,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm CivilComments,helm_classic_240829.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Helm CivilComments,helm_classic_240829.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836
aggregate,aggregate,Helm CivilComments,helm_classic_240829.csv,kendall,random,10,8,0.6,0.016666115520282188
aggregate,aggregate,Helm CivilComments,helm_classic_240829.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836
aggregate,aggregate,Helm RAFT,helm_classic_240829.csv,kendall,random,10,0,0.49441323247304414,0.048193488293190756
aggregate,aggregate,Helm RAFT,helm_classic_240829.csv,kendall,random,10,1,0.49441323247304414,0.048193488293190756
aggregate,aggregate,Helm RAFT,helm_classic_240829.csv,kendall,random,10,2,0.49441323247304414,0.048193488293190756
aggregate,aggregate,Helm RAFT,helm_classic_240829.csv,kendall,random,10,3,0.49441323247304414,0.048193488293190756
aggregate,aggregate,Helm RAFT,helm_classic_240829.csv,kendall,random,10,4,0.49441323247304414,0.048193488293190756
aggregate,aggregate,Helm RAFT,helm_classic_240829.csv,kendall,random,10,5,0.49441323247304414,0.048193488293190756
aggregate,aggregate,Helm RAFT,helm_classic_240829.csv,kendall,random,10,6,0.49441323247304414,0.048193488293190756
aggregate,aggregate,Helm RAFT,helm_classic_240829.csv,kendall,random,10,7,0.49441323247304414,0.048193488293190756
aggregate,aggregate,Helm RAFT,helm_classic_240829.csv,kendall,random,10,8,0.49441323247304414,0.048193488293190756
aggregate,aggregate,Helm RAFT,helm_classic_240829.csv,kendall,random,10,9,0.49441323247304414,0.048193488293190756
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,10,1,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,10,4,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,10,5,0.6888888888888888,0.00468694885361552
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,10,6,0.9999999999999999,5.511463844797178e-07
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552
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,10,4,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,10,5,0.6444444444444444,0.009148478835978836
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,10,7,0.6,0.016666115520282188
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,5,0.6,0.016666115520282188
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,10,8,0.7333333333333333,0.002212852733686067
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,10,1,0.7640931774583409,0.002263469812035174
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,10,2,0.8539864924534399,0.0006436975254696865
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,10,4,0.8090398349558905,0.0012254240706707103
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,10,5,0.6888888888888888,0.00468694885361552
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,10,7,0.7191465199607915,0.004057136032371292
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,10,8,0.7191465199607915,0.004057136032371292
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,0,0.5111111111111111,0.04662257495590829
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,1,0.6,0.016666115520282188
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,3,0.5555555555555555,0.02860945767195767
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,4,0.5555555555555555,0.02860945767195767
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,5,0.6444444444444444,0.009148478835978836
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,6,0.6,0.016666115520282188
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,7,0.6,0.016666115520282188
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,8,0.6,0.016666115520282188
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,9,0.6292532049656926,0.011921001496914019
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,0,0.6,0.016666115520282188
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,1,0.6,0.016666115520282188
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,3,0.6444444444444444,0.009148478835978836
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,4,0.5843065474681431,0.019550269092885535
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,5,0.4222222222222222,0.10831349206349207
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,6,0.7640931774583409,0.002263469812035174
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,7,0.6,0.016666115520282188
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,8,0.40451991747794525,0.1059975484249457
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,9,0.7501937734175208,0.0029250200956793346
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,0,0.6,0.016666115520282188
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,1,0.6,0.016666115520282188
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,3,0.6444444444444444,0.009148478835978836
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,10,5,0.5111111111111111,0.04662257495590829
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,8,0.5555555555555555,0.02860945767195767
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,1,0.7640931774583409,0.002263469812035174
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,2,0.7191465199607915,0.004057136032371292
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,3,0.5555555555555555,0.02860945767195767
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,4,0.6440611887195306,0.011244704061853582
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,5,0.5555555555555555,0.02860945767195767
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,6,0.7501937734175208,0.0029250200956793346
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,7,0.6292532049656926,0.011921001496914019
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,10,9,0.5843065474681431,0.019550269092885535
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,0,0.5111111111111111,0.04662257495590829
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,1,0.6,0.016666115520282188
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
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,10,5,0.5555555555555555,0.02860945767195767
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,7,0.5111111111111111,0.04662257495590829
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,8,0.5111111111111111,0.04662257495590829
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,10,1,0.6,0.016666115520282188
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,10,2,0.6,0.016666115520282188
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,10,3,0.6,0.016666115520282188
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,10,4,0.5111111111111111,0.04662257495590829
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,10,5,0.6444444444444444,0.009148478835978836
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,10,6,0.5555555555555555,0.02860945767195767
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,10,7,0.6,0.016666115520282188
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,0,0.4666666666666666,0.07255015432098766
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,1,0.4494665749754947,0.07248608508684644
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,2,0.4494665749754947,0.07248608508684644
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,3,0.5393598899705937,0.03114121059579671
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,4,0.40451991747794525,0.1059975484249457
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,5,0.5393598899705937,0.03114121059579671
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,6,0.4494665749754947,0.07248608508684644
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,7,0.5393598899705937,0.03114121059579671
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,8,0.4666666666666666,0.07255015432098766
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,9,0.5393598899705937,0.03114121059579671
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,10,1,0.6,0.016666115520282188
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,10,2,0.5555555555555555,0.02860945767195767
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,10,3,0.6,0.016666115520282188
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,10,4,0.5111111111111111,0.04662257495590829
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,10,5,0.6444444444444444,0.009148478835978836
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,10,6,0.5555555555555555,0.02860945767195767
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,10,7,0.6,0.016666115520282188
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,1,0.6,0.016666115520282188
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,2,0.6,0.016666115520282188
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,3,0.6,0.016666115520282188
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,4,0.5111111111111111,0.04662257495590829
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,5,0.6,0.016666115520282188
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,6,0.5555555555555555,0.02860945767195767
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,7,0.6,0.016666115520282188
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,9,0.6,0.016666115520282188
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,0,0.5111111111111111,0.04662257495590829
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,1,0.4222222222222222,0.10831349206349207
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,2,0.4666666666666666,0.07255015432098766
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,3,0.3333333333333333,0.21637345679012346
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,4,0.3333333333333333,0.21637345679012346
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,5,0.4222222222222222,0.10831349206349207
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,6,0.37777777777777777,0.1557418430335097
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,7,0.3333333333333333,0.21637345679012346
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,8,0.5111111111111111,0.04662257495590829
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,9,0.4222222222222222,0.10831349206349207
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,10,1,0.6,0.016666115520282188
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,10,3,0.6,0.016666115520282188
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,10,4,0.5111111111111111,0.04662257495590829
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,10,5,0.6888888888888888,0.00468694885361552
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,10,6,0.5555555555555555,0.02860945767195767
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,10,7,0.6,0.016666115520282188
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,10,8,0.6444444444444444,0.009148478835978836
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552
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,10,1,0.6888888888888888,0.00468694885361552
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,2,0.6888888888888888,0.00468694885361552
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,4,0.6,0.016666115520282188
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,5,0.6888888888888888,0.00468694885361552
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,6,0.6444444444444444,0.009148478835978836
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,10,0,0.3595732599803958,0.15076277502664528
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,10,1,0.44946657497549475,0.07248608508684644
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,10,2,0.3333333333333333,0.21637345679012346
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,10,3,0.1797866299901979,0.47249761400068846
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,10,4,0.31462660248284624,0.2086677876982641
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,10,5,0.13483997249264842,0.590013887163346
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,10,6,0.26967994498529685,0.2811980995641792
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,10,7,0.1797866299901979,0.47249761400068846
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,10,8,0.3595732599803958,0.15076277502664528
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,10,9,0.13483997249264842,0.590013887163346
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,10,1,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.5111111111111111,0.04662257495590829
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.5555555555555555,0.02860945767195767
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.7333333333333333,0.002212852733686067
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.6,0.016666115520282188
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06
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,10,8,0.7333333333333333,0.002212852733686067
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.5111111111111111,0.04662257495590829
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.37777777777777777,0.1557418430335097
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.6,0.016666115520282188
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.5555555555555555,0.02860945767195767
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.6,0.016666115520282188
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,10,6,0.7333333333333333,0.002212852733686067
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.4666666666666666,0.07255015432098766
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.5111111111111111,0.04662257495590829
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.9555555555555554,5.5114638447971785e-06
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,10,9,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.6,0.016666115520282188
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.5111111111111111,0.04662257495590829
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.6,0.016666115520282188
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.4666666666666666,0.07255015432098766
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.5555555555555555,0.02860945767195767
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.5555555555555555,0.02860945767195767
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.6,0.016666115520282188
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,BigBench,biggen_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836
aggregate,aggregate,BigBench,biggen_240829.csv,kendall,random,10,1,0.4666666666666666,0.07255015432098766
aggregate,aggregate,BigBench,biggen_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369
aggregate,aggregate,BigBench,biggen_240829.csv,kendall,random,10,3,0.4222222222222222,0.10831349206349207
aggregate,aggregate,BigBench,biggen_240829.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067
aggregate,aggregate,BigBench,biggen_240829.csv,kendall,random,10,5,0.4222222222222222,0.10831349206349207
aggregate,aggregate,BigBench,biggen_240829.csv,kendall,random,10,6,0.6444444444444444,0.009148478835978836
aggregate,aggregate,BigBench,biggen_240829.csv,kendall,random,10,7,0.6,0.016666115520282188
aggregate,aggregate,BigBench,biggen_240829.csv,kendall,random,10,8,0.6444444444444444,0.009148478835978836
aggregate,aggregate,BigBench,biggen_240829.csv,kendall,random,10,9,0.5111111111111111,0.04662257495590829
aggregate,aggregate,BigBench Grounding,biggen_240829.csv,kendall,random,10,0,0.4666666666666666,0.07255015432098766
aggregate,aggregate,BigBench Grounding,biggen_240829.csv,kendall,random,10,1,0.28888888888888886,0.2912483465608466
aggregate,aggregate,BigBench Grounding,biggen_240829.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836
aggregate,aggregate,BigBench Grounding,biggen_240829.csv,kendall,random,10,3,0.37777777777777777,0.1557418430335097
aggregate,aggregate,BigBench Grounding,biggen_240829.csv,kendall,random,10,4,0.6888888888888888,0.00468694885361552
aggregate,aggregate,BigBench Grounding,biggen_240829.csv,kendall,random,10,5,0.4222222222222222,0.10831349206349207
aggregate,aggregate,BigBench Grounding,biggen_240829.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552
aggregate,aggregate,BigBench Grounding,biggen_240829.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836
aggregate,aggregate,BigBench Grounding,biggen_240829.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552
aggregate,aggregate,BigBench Grounding,biggen_240829.csv,kendall,random,10,9,0.4222222222222222,0.10831349206349207
aggregate,aggregate,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,0,0.6,0.016666115520282188
aggregate,aggregate,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,1,0.37777777777777777,0.1557418430335097
aggregate,aggregate,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,3,0.24444444444444444,0.38071979717813054
aggregate,aggregate,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,4,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,5,0.4222222222222222,0.10831349206349207
aggregate,aggregate,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,6,0.6444444444444444,0.009148478835978836
aggregate,aggregate,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,7,0.5111111111111111,0.04662257495590829
aggregate,aggregate,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552
aggregate,aggregate,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,9,0.5111111111111111,0.04662257495590829
aggregate,aggregate,BigBench Planning,biggen_240829.csv,kendall,random,10,0,0.6,0.016666115520282188
aggregate,aggregate,BigBench Planning,biggen_240829.csv,kendall,random,10,1,0.37777777777777777,0.1557418430335097
aggregate,aggregate,BigBench Planning,biggen_240829.csv,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,BigBench Planning,biggen_240829.csv,kendall,random,10,3,0.3146266024828463,0.2086677876982641
aggregate,aggregate,BigBench Planning,biggen_240829.csv,kendall,random,10,4,0.6888888888888888,0.00468694885361552
aggregate,aggregate,BigBench Planning,biggen_240829.csv,kendall,random,10,5,0.4222222222222222,0.10831349206349207
aggregate,aggregate,BigBench Planning,biggen_240829.csv,kendall,random,10,6,0.5843065474681431,0.019550269092885535
aggregate,aggregate,BigBench Planning,biggen_240829.csv,kendall,random,10,7,0.49441323247304414,0.048193488293190756
aggregate,aggregate,BigBench Planning,biggen_240829.csv,kendall,random,10,8,0.6444444444444444,0.009148478835978836
aggregate,aggregate,BigBench Planning,biggen_240829.csv,kendall,random,10,9,0.4666666666666666,0.07255015432098766
aggregate,aggregate,BigBench Reasoning,biggen_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836
aggregate,aggregate,BigBench Reasoning,biggen_240829.csv,kendall,random,10,1,0.4666666666666666,0.07255015432098766
aggregate,aggregate,BigBench Reasoning,biggen_240829.csv,kendall,random,10,2,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,BigBench Reasoning,biggen_240829.csv,kendall,random,10,3,0.28888888888888886,0.2912483465608466
aggregate,aggregate,BigBench Reasoning,biggen_240829.csv,kendall,random,10,4,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,BigBench Reasoning,biggen_240829.csv,kendall,random,10,5,0.4222222222222222,0.10831349206349207
aggregate,aggregate,BigBench Reasoning,biggen_240829.csv,kendall,random,10,6,0.6,0.016666115520282188
aggregate,aggregate,BigBench Reasoning,biggen_240829.csv,kendall,random,10,7,0.6,0.016666115520282188
aggregate,aggregate,BigBench Reasoning,biggen_240829.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552
aggregate,aggregate,BigBench Reasoning,biggen_240829.csv,kendall,random,10,9,0.4222222222222222,0.10831349206349207
aggregate,aggregate,BigBench Refinement,biggen_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552
aggregate,aggregate,BigBench Refinement,biggen_240829.csv,kendall,random,10,1,0.5555555555555555,0.02860945767195767
aggregate,aggregate,BigBench Refinement,biggen_240829.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067
aggregate,aggregate,BigBench Refinement,biggen_240829.csv,kendall,random,10,3,0.5111111111111111,0.04662257495590829
aggregate,aggregate,BigBench Refinement,biggen_240829.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102
aggregate,aggregate,BigBench Refinement,biggen_240829.csv,kendall,random,10,5,0.5111111111111111,0.04662257495590829
aggregate,aggregate,BigBench Refinement,biggen_240829.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,BigBench Refinement,biggen_240829.csv,kendall,random,10,7,0.6,0.016666115520282188
aggregate,aggregate,BigBench Refinement,biggen_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067
aggregate,aggregate,BigBench Refinement,biggen_240829.csv,kendall,random,10,9,0.4666666666666666,0.07255015432098766
aggregate,aggregate,BigBench Safety,biggen_240829.csv,kendall,random,10,0,0.28888888888888886,0.2912483465608466
aggregate,aggregate,BigBench Safety,biggen_240829.csv,kendall,random,10,1,0.24444444444444444,0.38071979717813054
aggregate,aggregate,BigBench Safety,biggen_240829.csv,kendall,random,10,2,0.5111111111111111,0.04662257495590829
aggregate,aggregate,BigBench Safety,biggen_240829.csv,kendall,random,10,3,0.24444444444444444,0.38071979717813054
aggregate,aggregate,BigBench Safety,biggen_240829.csv,kendall,random,10,4,0.24444444444444444,0.38071979717813054
aggregate,aggregate,BigBench Safety,biggen_240829.csv,kendall,random,10,5,0.19999999999999998,0.4843127204585538
aggregate,aggregate,BigBench Safety,biggen_240829.csv,kendall,random,10,6,0.4666666666666666,0.07255015432098766
aggregate,aggregate,BigBench Safety,biggen_240829.csv,kendall,random,10,7,0.3333333333333333,0.21637345679012346
aggregate,aggregate,BigBench Safety,biggen_240829.csv,kendall,random,10,8,0.4666666666666666,0.07255015432098766
aggregate,aggregate,BigBench Safety,biggen_240829.csv,kendall,random,10,9,0.3333333333333333,0.21637345679012346
aggregate,aggregate,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,0,0.5111111111111111,0.04662257495590829
aggregate,aggregate,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,1,0.3333333333333333,0.21637345679012346
aggregate,aggregate,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,2,0.6888888888888888,0.00468694885361552
aggregate,aggregate,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,3,0.3333333333333333,0.21637345679012346
aggregate,aggregate,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,4,0.5555555555555555,0.02860945767195767
aggregate,aggregate,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,5,0.3333333333333333,0.21637345679012346
aggregate,aggregate,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,6,0.5111111111111111,0.04662257495590829
aggregate,aggregate,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,7,0.4666666666666666,0.07255015432098766
aggregate,aggregate,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,8,0.6,0.016666115520282188
aggregate,aggregate,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,9,0.37777777777777777,0.1557418430335097
aggregate,aggregate,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,0,0.5555555555555555,0.02860945767195767
aggregate,aggregate,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,1,0.28888888888888886,0.2912483465608466
aggregate,aggregate,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,2,0.8090398349558905,0.0012254240706707103
aggregate,aggregate,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,3,0.35957325998039574,0.15076277502664528
aggregate,aggregate,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,4,0.7777777777777777,0.0009463183421516755
aggregate,aggregate,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,5,0.4494665749754947,0.07248608508684644
aggregate,aggregate,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552
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,10,8,0.6444444444444444,0.009148478835978836
aggregate,aggregate,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,9,0.49441323247304414,0.048193488293190756
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,10,0,0.5555555555555555,0.02860945767195767
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,10,1,0.6,0.016666115520282188
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,10,2,0.6,0.016666115520282188
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,10,3,0.5111111111111111,0.04662257495590829
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,10,5,0.5555555555555555,0.02860945767195767
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,10,7,0.5111111111111111,0.04662257495590829
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,10,8,0.5555555555555555,0.02860945767195767
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,10,9,0.5555555555555555,0.02860945767195767
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,0,0.5683286162253945,0.02418521832271127
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,1,0.7501937734175208,0.0029250200956793346
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,2,0.6592611948214576,0.008926875535053643
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,3,0.522862326927363,0.03809415806109578
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,4,0.5393598899705937,0.03114121059579671
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,5,0.6137949055234262,0.01491204965521593
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,6,0.6137949055234262,0.01491204965521593
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,7,0.522862326927363,0.03809415806109578
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,8,0.5683286162253945,0.02418521832271127
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,9,0.6137949055234262,0.01491204965521593
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,0,0.5555555555555555,0.02860945767195767
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,1,0.6,0.016666115520282188
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,2,0.5555555555555555,0.02860945767195767
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,3,0.5111111111111111,0.04662257495590829
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,4,0.6,0.016666115520282188
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,5,0.5111111111111111,0.04662257495590829
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,6,0.6444444444444444,0.009148478835978836
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,7,0.5111111111111111,0.04662257495590829
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,8,0.5555555555555555,0.02860945767195767
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,9,0.5111111111111111,0.04662257495590829
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,0,0.5555555555555555,0.02860945767195767
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,1,0.6444444444444444,0.009148478835978836
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,2,0.6,0.016666115520282188
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,3,0.5111111111111111,0.04662257495590829
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,4,0.6,0.016666115520282188
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,5,0.6,0.016666115520282188
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,7,0.5111111111111111,0.04662257495590829
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,8,0.5555555555555555,0.02860945767195767
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,9,0.6,0.016666115520282188
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,0,0.37777777777777777,0.1557418430335097
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,1,0.4666666666666666,0.07255015432098766
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,2,0.3333333333333333,0.21637345679012346
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,3,0.3333333333333333,0.21637345679012346
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,4,0.4222222222222222,0.10831349206349207
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,5,0.4222222222222222,0.10831349206349207
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,6,0.5111111111111111,0.04662257495590829
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,7,0.3333333333333333,0.21637345679012346
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,8,0.37777777777777777,0.1557418430335097
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,9,0.4222222222222222,0.10831349206349207
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,10,0,0.5555555555555555,0.02860945767195767
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,10,1,0.5555555555555555,0.02860945767195767
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,10,2,0.6,0.016666115520282188
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,10,3,0.5111111111111111,0.04662257495590829
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,10,4,0.6888888888888888,0.00468694885361552
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,10,5,0.6,0.016666115520282188
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,10,6,0.6444444444444444,0.009148478835978836
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,10,7,0.5111111111111111,0.04662257495590829
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,10,8,0.5555555555555555,0.02860945767195767
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,10,9,0.6,0.016666115520282188
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,1,0.6,0.016666115520282188
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,2,0.6888888888888888,0.00468694885361552
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,3,0.6,0.016666115520282188
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,4,0.6888888888888888,0.00468694885361552
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,7,0.6,0.016666115520282188
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,8,0.6444444444444444,0.009148478835978836
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067