Spaces:
Running
Running
| model,score | |
| arx_0.3,1.0 | |
| claude_3.5_sonnet,0.9876543209876543 | |
| grok_2,0.9753086419753086 | |
| gpt_4o_2024_05_13,0.9629629629629629 | |
| grok_2_mini,0.9506172839506173 | |
| gemini_1.5_pro,0.9382716049382716 | |
| claude_3_opus,0.9259259259259259 | |
| qwen2_72b_chat,0.9135802469135802 | |
| magnum_72b_v1,0.9012345679012346 | |
| gpt_4_turbo,0.8888888888888888 | |
| deepseek_coder_v2_instruct,0.8765432098765432 | |
| higgs_llama3_70b,0.8641975308641975 | |
| gpt_4o_mini,0.8518518518518519 | |
| llama3.1_70b_instruct,0.8395061728395061 | |
| gemini_1.5_flash,0.8271604938271605 | |
| yi_large,0.8148148148148148 | |
| claude_3_sonnet,0.8024691358024691 | |
| llama3_70b_instruct,0.7901234567901234 | |
| phi3_medium_4k,0.7777777777777778 | |
| qwen2_72b_32k,0.7654320987654321 | |
| deepseek_v2_chat,0.7530864197530864 | |
| llama3_70b,0.7407407407407407 | |
| qwen1.5_72b_chat,0.7283950617283951 | |
| llama3.1_70b,0.7160493827160493 | |
| yi_1.5_34b_chat,0.7037037037037037 | |
| gemma_2_9b_it,0.691358024691358 | |
| phi3_medium_128k,0.6790123456790124 | |
| mammoth2_8x7b_plus,0.6666666666666666 | |
| qwen1.5_110b,0.654320987654321 | |
| glm_4_9b_chat,0.6419753086419753 | |
| glm_4_9b,0.6296296296296297 | |
| phi_3.5_mini_instruct,0.6172839506172839 | |
| qwen2_7b_instruct,0.6049382716049383 | |
| yi_1.5_9b_chat,0.5925925925925926 | |
| phi3_mini_4k,0.5802469135802469 | |
| gemma_2_9b,0.5679012345679012 | |
| mistral_nemo_instruct_2407,0.5555555555555556 | |
| llama3.1_8b_instruct,0.5432098765432098 | |
| phi3_mini_128k,0.5308641975308642 | |
| mammoth2_8b_plus,0.5185185185185185 | |
| mixtral_8x7b_instruct_v0.1,0.5061728395061729 | |
| yi_34b,0.49382716049382713 | |
| mathstral_7b_v0.1,0.48148148148148145 | |
| deepseek_coder_v2_lite_instruct,0.4691358024691358 | |
| mixtral_8x7b_v0.1,0.4567901234567901 | |
| llama3_8b_instruct,0.4444444444444444 | |
| mammoth2_7b_plus,0.43209876543209874 | |
| qwen2_7b,0.41975308641975306 | |
| mistral_nemo_base_2407,0.4074074074074074 | |
| wizardlm_2_8x22b,0.3950617283950617 | |
| yi_1.5_6b_chat,0.38271604938271603 | |
| qwen1.5_14b_chat,0.37037037037037035 | |
| c4ai_command_r_v01,0.345679012345679 | |
| staring_7b,0.345679012345679 | |
| llama_2_70b,0.3333333333333333 | |
| openchat_3.5_8b,0.32098765432098764 | |
| internmath_20b_plus,0.30864197530864196 | |
| llama3_smaug_8b,0.2962962962962963 | |
| llama3.1_8b,0.2839506172839506 | |
| llama3_8b,0.2716049382716049 | |
| deepseekmath_7b_instruct,0.25925925925925924 | |
| deepseek_coder_v2_lite_base,0.24691358024691357 | |
| gemma_7b,0.2345679012345679 | |
| internmath_7b_plus,0.2222222222222222 | |
| zephyr_7b_beta,0.20987654320987653 | |
| mistral_7b_v0.1,0.19753086419753085 | |
| mistral_7b_instruct_v0.2,0.18518518518518517 | |
| mistral_7b_v0.2,0.1728395061728395 | |
| qwen1.5_7b_chat,0.16049382716049382 | |
| yi_6b_chat,0.14814814814814814 | |
| neo_7b_instruct,0.13580246913580246 | |
| yi_6b,0.12345679012345678 | |
| neo_7b,0.1111111111111111 | |
| mistral_7b_instruct_v0.1,0.09876543209876543 | |
| llama_2_13b,0.08641975308641975 | |
| llemma_7b,0.07407407407407407 | |
| qwen2_1.5b_instruct,0.06172839506172839 | |
| qwen2_1.5b,0.04938271604938271 | |
| llama_2_7b,0.037037037037037035 | |
| qwen2_0.5b_instruct,0.024691358024691357 | |
| gemma_2b,0.012345679012345678 | |
| qwen2_0.5b,0.0 | |