Spaces:
Running
Running
| model,score | |
| gemini_1_5_pro_api_0409_preview,1.0 | |
| gemini_1_5_pro_exp_0801,0.9921875 | |
| chatgpt_4o_latest,0.984375 | |
| gpt_3_5_turbo_0314,0.9765625 | |
| bard_jan_24_gemini_pro,0.96875 | |
| claude_1,0.9609375 | |
| gemini_advanced_0514,0.953125 | |
| llama3_1_70b_instruct,0.9453125 | |
| gpt_4o_2024_05_13,0.9375 | |
| gpt_4o_2024_08_06,0.9296875 | |
| gpt_4o_mini_2024_07_18,0.921875 | |
| claude_3_5_sonnet_20240620,0.9140625 | |
| claude_3_opus_20240229,0.90625 | |
| athene_70b_0725,0.8984375 | |
| gemini_pro_dev_api,0.890625 | |
| claude_2_0,0.8828125 | |
| glm_4_0520,0.875 | |
| nemotron_4_340b_instruct,0.8671875 | |
| yi_large_preview,0.859375 | |
| llama_2_70b_chat,0.8515625 | |
| reka_core_20240722,0.84375 | |
| gemini_1_5_pro_api_0514,0.8359375 | |
| gemini_pro,0.828125 | |
| llama3_1_405b_instruct,0.8203125 | |
| mistral_large_2407,0.8125 | |
| gpt_4_turbo_2024_04_09,0.8046875 | |
| gpt_4_1106_preview,0.796875 | |
| gpt_3_5_turbo_0613,0.7890625 | |
| gpt_4_0125_preview,0.78125 | |
| glm_4_0116,0.7734375 | |
| zephyr_orpo_141b_a35b_v0_1,0.765625 | |
| qwen_max_0428,0.7578125 | |
| claude_instant_1,0.75 | |
| yi_large,0.7421875 | |
| deepseek_coder_v2_0724,0.734375 | |
| deepseek_v2_api_0628,0.7265625 | |
| gemini_1_5_flash_api_0514,0.71875 | |
| llama3_70b_instruct,0.7109375 | |
| command_r_plus,0.703125 | |
| gpt_4_0314,0.6953125 | |
| claude_2_1,0.6875 | |
| wizardlm_70b,0.6796875 | |
| gemma_2_27b_it,0.671875 | |
| dolphin_2_2_1_mistral_7b,0.6640625 | |
| guanaco_33b,0.65625 | |
| nous_hermes_2_mixtral_8x7b_dpo,0.6484375 | |
| wizardlm_13b,0.640625 | |
| mpt_30b_chat,0.6328125 | |
| qwen1_5_110b_chat,0.625 | |
| claude_3_sonnet_20240229,0.6171875 | |
| mistral_next,0.609375 | |
| deepseek_coder_v2,0.6015625 | |
| reka_flash_21b_20240226_online,0.59375 | |
| starling_lm_7b_beta,0.5859375 | |
| llama2_70b_steerlm_chat,0.578125 | |
| mistral_medium,0.5703125 | |
| llama_2_13b_chat,0.5625 | |
| tulu_2_dpo_70b,0.5546875 | |
| reka_core_20240501,0.546875 | |
| gpt_4_0613,0.5390625 | |
| deepseek_llm_67b_chat,0.53125 | |
| solar_10_7b_instruct_v1_0,0.5234375 | |
| openchat_3_5_0106,0.515625 | |
| reka_flash_20240722,0.5078125 | |
| gemma_2_9b_it,0.5 | |
| llama3_1_8b_instruct,0.4921875 | |
| openchat_3_5,0.484375 | |
| pplx_7b_online,0.4765625 | |
| qwen1_5_72b_chat,0.46875 | |
| zephyr_7b_alpha,0.4609375 | |
| claude_3_haiku_20240307,0.453125 | |
| starling_lm_7b_alpha,0.4453125 | |
| reka_flash_21b_20240226,0.4375 | |
| mistral_large_2402,0.4296875 | |
| gpt_3_5_turbo_1106,0.421875 | |
| qwen1_5_7b_chat,0.4140625 | |
| reka_flash_preview_20240611,0.40625 | |
| yi_1_5_34b_chat,0.3984375 | |
| openhermes_2_5_mistral_7b,0.390625 | |
| codellama34b_instruct,0.3828125 | |
| qwen1_5_14b_chat,0.375 | |
| yi_34b_chat,0.3671875 | |
| pplx_70b_online,0.359375 | |
| qwen2_72b_instruct,0.3515625 | |
| dbrx_instructruct_preview,0.34375 | |
| llama3_8b_instruct,0.3359375 | |
| falcon_180b_chat,0.328125 | |
| palm_2,0.3203125 | |
| qwen_14b_chat,0.3125 | |
| stripedhyena_nous_7b,0.3046875 | |
| qwen1_5_32b_chat,0.296875 | |
| command_r,0.2890625 | |
| gemma_7b_it,0.28125 | |
| zephyr_7b_beta,0.2734375 | |
| mixtral_8x22b_instruct_v0_1,0.265625 | |
| vicuna_7b,0.2578125 | |
| snowflake_arctic_instruct,0.25 | |
| vicuna_33b,0.2421875 | |
| gemma_2_2b_it,0.234375 | |
| koala_13b,0.2265625 | |
| gpt_3_5_turbo_0125,0.21875 | |
| mistral_7b_instruct,0.2109375 | |
| llama_2_7b_chat,0.203125 | |
| mistral_7b_instruct_v0_2,0.1953125 | |
| gemma_1_1_7b_it,0.1875 | |
| gpt4all_13b_snoozy,0.1796875 | |
| phi_3_small_8k_instruct,0.171875 | |
| olmo_7b_instruct,0.1640625 | |
| phi_3_mini_4k_instruct,0.15625 | |
| phi_3_mini_128k_instruct,0.1484375 | |
| rwkv_4_raven_14b,0.140625 | |
| vicuna_13b,0.1328125 | |
| codellama_70b_instruct,0.125 | |
| mpt_7b_chat,0.1171875 | |
| mixtral_8x7b_instruct_v0_1,0.109375 | |
| phi_3_medium_4k_instruct,0.1015625 | |
| gemma_2b_it,0.09375 | |
| phi_3_mini_4k_instruct_june_2024,0.0859375 | |
| qwen1_5_4b_chat,0.078125 | |
| chatglm_6b,0.0703125 | |
| alpaca_13b,0.0625 | |
| gemma_1_1_2b_it,0.0546875 | |
| chatglm2_6b,0.046875 | |
| stablelm_tuned_alpha_7b,0.0390625 | |
| chatglm3_6b,0.03125 | |
| oasst_pythia_12b,0.0234375 | |
| llama_13b,0.015625 | |
| fastchat_t5_3b,0.0078125 | |
| dolly_v2_12b,0.0 | |