BiGGen-Bench-Leaderboard / data /bgb-leaderboard-gpt-4-turbo-2024-04-09.csv
scottsuk0306's picture
Update
07a2125
raw
history blame contribute delete
No virus
9.3 kB
Grounding ⚑️,Instruction Following πŸ“,Planning πŸ“…,Reasoning πŸ’‘,Refinement πŸ”©,Safety ⚠️,Theory of Mind πŸ€”,Tool Usage πŸ› οΈ,Multilingual πŸ‡¬πŸ‡«,Model πŸ€—,Model Params (B),Model Type,Average
4.288,4.23,4.271,4.22,4.171,4.565,4.24,3.775,3.6,gpt-4-1106-preview,,Proprietary,4.22
4.3,4.2,4.357,4.16,4.145,4.174,4.26,3.925,3.543,gpt-4-0125-preview,,Proprietary,4.19
4.238,4.26,4.357,4.21,4.079,4.058,4.08,3.85,3.643,gpt-4o-2024-05-13,,Proprietary,4.141
4.312,4.13,4.3,4.2,4.105,4.087,4.12,3.8,3.471,gpt-4-turbo-2024-04-09,,Proprietary,4.132
4.288,4.06,4.186,3.97,3.908,4.536,4.09,3.788,3.571,claude-3-opus-20240229,,Proprietary,4.103
4.125,4.18,4.186,3.87,3.907,4.014,4.04,3.775,3.314,meta-llama/Meta-Llama-3-70B-Instruct,70.0,Chat,4.012
4.25,3.92,4.171,3.91,3.724,4.362,4.0,3.75,3.186,claude-3-sonnet-20240229,,Proprietary,4.011
4.15,4.01,4.229,3.94,3.882,4.043,3.99,3.588,2.771,qwen/qwen-110b-chat,110.0,Chat,3.979
4.138,4.01,4.129,3.69,3.632,4.304,3.98,3.75,3.071,claude-3-haiku-20240307,,Proprietary,3.954
4.05,4.04,4.129,4.06,3.671,4.116,4.07,3.488,3.257,gemini-pro-1.5,,Proprietary,3.953
4.012,4.0,4.0,3.96,3.842,4.087,3.87,3.712,2.714,MaziyarPanahi/Mixtral-8x22B-Instruct-v0.1-AWQ,141,Chat,3.936
3.962,3.94,4.029,3.95,3.776,4.058,3.9,3.862,2.929,mistral-medium,,Proprietary,3.935
4.025,3.99,4.029,3.93,3.776,3.913,3.93,3.825,2.886,mistral-large,,Proprietary,3.927
4.138,3.91,3.971,3.92,3.453,4.217,3.96,3.625,2.671,google/gemini-flash-1.5,,Proprietary,3.899
3.988,4.0,4.186,3.64,3.461,3.971,3.94,3.525,2.757,alpindale/c4ai-command-r-plus-GPTQ,104,Chat,3.839
3.888,3.99,4.029,3.68,3.632,3.957,3.96,3.525,2.914,Qwen/Qwen1.5-72B-Chat,72.0,Chat,3.832
3.725,3.88,3.8,3.81,3.974,4.145,3.9,3.338,1.914,microsoft/Phi-3-mini-4k-instruct,3.8,Chat,3.821
3.788,3.85,4.029,3.62,3.395,4.217,3.87,3.738,2.714,Qwen/Qwen1.5-32B-Chat,32.0,Chat,3.813
3.8,3.84,4.0,3.56,3.547,3.87,3.87,3.562,2.271,Starling-LM-7B-beta,7.0,Chat,3.756
4.125,3.94,3.929,3.47,3.507,3.725,3.83,3.5,2.914,meta-llama/Meta-Llama-3-8B-Instruct,8.0,Chat,3.753
3.812,4.06,3.957,3.53,3.342,3.739,3.79,3.662,2.557,NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO,46.7,Chat,3.737
3.738,3.83,3.914,3.57,3.676,3.884,3.96,3.038,2.186,01-ai/Yi-34B-Chat,34.0,Chat,3.701
3.9,3.88,3.6,3.71,3.434,3.812,3.81,3.412,2.714,mistralai/Mixtral-8x7B-Instruct-v0.1,46.7,Chat,3.695
3.925,3.85,3.843,3.65,3.434,3.884,3.79,3.138,2.614,gpt-3.5-turbo-0125,,Proprietary,3.689
3.7,3.89,3.9,3.36,3.421,3.754,3.83,3.612,2.314,allenai/tulu-2-dpo-70b,70.0,Chat,3.683
3.712,3.8,3.7,3.82,3.513,3.957,3.83,3.1,1.829,microsoft/Phi-3-mini-128k-instruct,3.8,Chat,3.679
4.025,3.79,3.829,3.51,3.434,4.0,3.67,3.162,2.557,gpt-3.5-turbo-1106,,Proprietary,3.678
3.812,3.88,3.9,3.39,3.447,3.899,3.9,3.188,2.186,CohereForAI/c4ai-command-r-v01,35.0,Chat,3.677
3.812,3.77,3.857,3.42,3.382,3.826,3.9,3.412,2.443,upstage/SOLAR-10.7B-Instruct-v1.0,10.7,Chat,3.672
3.662,3.88,3.929,3.22,3.36,4.377,3.73,3.188,2.386,meta-llama/Llama-2-70b-chat-hf,70.0,Chat,3.668
3.6,3.84,3.871,3.62,3.373,3.942,3.75,3.125,3.186,gemini-1.0-pro,,Proprietary,3.64
3.7,3.87,3.8,3.18,3.447,3.826,3.77,3.362,2.286,mistralai/Mistral-7B-Instruct-v0.2,7.0,Chat,3.619
3.688,3.7,3.743,3.5,3.539,4.0,3.49,3.188,,mistral-community/Mixtral-8x22B-v0.1-AWQ,141,Base,3.606
3.65,3.78,3.714,3.39,3.461,3.609,3.63,3.538,2.4,NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT,46.7,Chat,3.596
3.638,3.84,3.757,3.34,3.566,3.725,3.66,3.125,2.157,openchat/openchat-3.5-0106,7.0,Chat,3.581
3.55,3.62,3.957,3.52,3.618,3.449,3.58,3.288,2.586,MaziyarPanahi/zephyr-orpo-141b-A35b-v0.1-AWQ,141,Chat,3.573
3.625,3.9,3.857,3.36,3.263,3.855,3.52,3.2,2.386,Qwen/Qwen1.5-14B-Chat,14.0,Chat,3.573
3.588,3.88,3.714,3.3,3.395,3.725,3.7,3.15,2.057,Qwen/Qwen1.5-7B-Chat,7.0,Chat,3.556
3.712,3.72,3.829,3.33,3.224,3.913,3.54,3.025,2.229,Starling-LM-7B-alpha,7.0,Chat,3.537
3.55,3.72,3.729,3.23,3.382,3.551,3.73,3.288,1.943,HuggingFaceH4/zephyr-7b-beta,7.0,Chat,3.522
3.662,3.74,3.8,3.26,3.355,3.377,3.69,3.062,2.171,NousResearch/Nous-Hermes-2-Mistral-7B-DPO,7.0,Chat,3.493
3.338,3.65,3.643,3.53,3.373,3.536,3.56,3.175,2.071,NousResearch/Nous-Hermes-2-Yi-34B,34.0,Chat,3.476
3.612,3.8,3.686,3.12,3.263,3.696,3.58,3.025,2.1,kaist-ai/mistral-orpo-beta,7.0,Chat,3.473
3.662,3.92,3.686,2.76,3.079,4.319,3.71,2.6,2.114,meta-llama/Llama-2-13b-chat-hf,13.0,Chat,3.467
3.688,3.66,3.729,3.28,3.276,3.435,3.57,3.062,2.1,teknium/OpenHermes-2.5-Mistral-7B,7.0,Chat,3.462
3.712,3.58,3.5,3.3,3.237,3.87,3.59,2.775,,mistralai/Mixtral-8x7B-v0.1,46.7,Base,3.445
3.525,3.7,3.6,3.11,3.171,3.971,3.5,2.95,2.086,kaist-ai/mistral-orpo-alpha,7.0,Chat,3.441
3.45,3.77,3.6,2.9,3.184,3.841,3.59,3.05,2.143,allenai/tulu-2-dpo-13b,13.0,Chat,3.423
3.488,3.6,3.5,3.25,3.227,3.942,3.38,2.988,,Qwen/Qwen1.5-72B,72.0,Base,3.422
3.45,3.51,3.686,3.01,3.211,3.652,3.5,3.35,2.0,allenai/codetulu-2-34b,34.0,Chat,3.421
3.588,3.53,3.371,3.25,3.25,4.043,3.44,2.788,2.0,google/gemma-1.1-7b-it,7.0,Chat,3.407
3.525,3.66,3.8,3.28,3.28,3.232,3.45,2.925,1.914,teknium/OpenHermes-2-Mistral-7B,7.0,Chat,3.394
3.5,3.5,3.457,3.04,3.079,4.13,3.46,2.738,2.114,codellama/CodeLlama-34b-Instruct-hf,34.0,Chat,3.363
3.512,3.54,3.529,3.27,3.24,3.58,3.39,2.512,,01-ai/Yi-34B,34.0,Base,3.322
3.425,3.56,3.386,3.06,3.133,3.87,3.48,2.625,,meta-llama/Llama-2-70b-hf,70.0,Base,3.317
3.325,3.64,3.514,3.31,3.118,3.333,3.33,2.925,,Qwen/Qwen1.5-32B,32.0,Base,3.312
3.388,3.58,3.586,2.85,2.961,4.145,3.65,2.3,2.029,meta-llama/Llama-2-7b-chat-hf,7.0,Chat,3.307
3.238,3.76,3.5,2.79,3.079,3.754,3.68,2.438,1.971,allenai/tulu-2-dpo-7b,7.0,Chat,3.28
3.225,3.5,3.4,2.8,3.197,3.29,3.38,3.238,1.886,allenai/codetulu-2-13b,13.0,Chat,3.254
3.25,3.56,3.371,2.96,3.197,3.667,3.42,2.562,,upstage/SOLAR-10.7B-v1.0,10.7,Base,3.248
3.15,3.38,3.4,2.8,3.027,3.768,3.39,2.775,2.029,allenai/tulu-2-13b,13.0,Chat,3.211
3.262,3.34,3.357,2.77,2.895,4.043,3.38,2.6,1.886,codellama/CodeLlama-13b-Instruct-hf,13.0,Chat,3.206
3.275,3.52,3.414,2.85,3.08,3.478,3.677,2.338,1.457,01-ai/Yi-6B-Chat,6.0,Chat,3.204
3.212,3.36,3.286,2.75,2.961,3.754,3.22,2.575,1.771,codellama/CodeLlama-7b-Instruct-hf,7.0,Chat,3.14
3.312,3.43,3.071,2.97,3.026,3.768,3.15,2.325,1.786,google/gemma-7b-it,7.0,Chat,3.132
3.35,3.33,3.114,3.04,3.342,3.261,3.04,2.5,,meta-llama/Meta-Llama-3-70B,70.0,Base,3.122
3.538,3.41,3.157,3.0,3.092,2.58,3.16,2.912,,Qwen/Qwen1.5-14B,14.0,Base,3.106
2.9,3.34,3.229,2.74,3.053,3.971,3.37,1.975,1.471,google/gemma-1.1-2b-it,2.0,Chat,3.072
3.112,3.41,3.114,2.73,2.908,3.246,3.25,2.788,1.8,allenai/codetulu-2-7b,7.0,Chat,3.07
2.862,3.34,3.229,2.81,2.974,3.638,3.26,2.212,1.714,allenai/tulu-2-7b,7.0,Chat,3.041
3.15,3.33,3.1,2.78,2.892,3.377,3.29,2.275,,mistral-community/Mistral-7B-v0.2,7.0,Base,3.024
3.225,3.3,3.243,2.86,2.763,3.406,3.09,2.162,,mistralai/Mistral-7B-v0.1,7.0,Base,3.006
2.9,3.19,3.086,2.83,3.0,3.333,3.07,2.4,1.471,Qwen/Qwen1.5-4B-Chat,4.0,Chat,2.976
3.112,3.54,3.271,2.47,2.776,3.101,3.31,2.212,1.414,allenai/OLMo-7B-Instruct,7.0,Chat,2.974
2.875,3.24,3.114,2.48,2.882,3.754,3.15,1.962,1.657,google/gemma-2b-it,2.0,Chat,2.932
2.988,3.14,3.014,2.65,2.827,3.101,2.77,2.488,,Qwen/Qwen1.5-7B,7.0,Base,2.872
3.138,2.92,2.857,2.8,2.763,3.406,3.2,1.788,,microsoft/phi-2,2.7,Base,2.859
2.95,3.27,2.957,2.4,2.684,3.333,2.93,2.088,1.186,allenai/OLMo-7B-SFT,7.0,Chat,2.827
2.85,2.7,2.671,2.83,2.747,4.101,2.55,1.988,1.929,codellama/CodeLlama-70b-Instruct-hf,70.0,Chat,2.805
2.988,2.97,2.743,2.75,2.816,2.971,2.84,2.088,,EleutherAI/llemma_34b,34.0,Base,2.771
3.262,2.94,2.657,2.39,3.039,2.899,2.82,1.938,,meta-llama/Meta-Llama-3-8B,8.0,Base,2.743
2.812,3.27,2.914,2.28,2.855,2.681,3.13,1.988,1.3,Qwen/Qwen1.5-1.8B-Chat,1.8,Chat,2.741
2.888,2.94,2.729,2.45,2.697,3.333,2.73,1.9,,Qwen/Qwen1.5-4B,4.0,Base,2.708
2.85,3.09,2.786,2.28,2.579,3.348,2.88,1.812,,meta-llama/Llama-2-13b-hf,13.0,Base,2.703
2.938,2.97,2.657,2.36,2.487,3.232,2.89,1.55,,01-ai/Yi-6B,6.0,Base,2.635
2.938,2.62,2.557,2.44,2.507,2.841,2.44,2.4,,codellama/CodeLlama-70b-hf,70.0,Base,2.593
2.812,2.66,2.486,2.17,2.566,2.725,2.59,2.062,,codellama/CodeLlama-34b-hf,34.0,Base,2.509
2.475,2.89,2.5,2.24,2.526,2.87,2.95,1.525,,microsoft/phi-1_5,1.3,Base,2.497
2.938,2.49,1.786,2.24,2.487,2.812,2.8,2.362,2.043,microsoft/Orca-2-13b,13.0,Chat,2.489
2.612,2.87,2.514,2.18,2.211,3.217,2.6,1.45,,meta-llama/Llama-2-7b-hf,7.0,Base,2.457
2.538,2.85,2.386,1.98,2.605,2.478,2.55,1.525,,Qwen/Qwen1.5-1.8B,1.8,Base,2.364
2.412,2.57,2.086,2.24,2.303,2.522,2.19,1.838,,EleutherAI/llemma_7b,7.0,Base,2.27
2.338,2.72,2.357,2.16,2.093,2.623,2.32,1.488,,google/gemma-2b,2.0,Base,2.262
2.3,2.3,1.957,2.01,2.092,2.449,2.15,1.812,,codellama/CodeLlama-13b-hf,13.0,Base,2.134
2.2,2.61,2.057,1.76,2.0,2.391,2.38,1.462,1.159,Qwen/Qwen1.5-0.5B-Chat,0.5,Chat,2.108
2.425,2.27,1.371,1.85,2.316,2.594,2.24,1.6,1.729,microsoft/Orca-2-7b,7.0,Chat,2.083
2.388,2.26,1.929,1.84,2.105,2.652,2.16,1.312,,allenai/OLMo-7B,7.0,Base,2.081
1.962,2.25,1.771,1.72,2.118,2.348,1.9,1.562,,codellama/CodeLlama-7b-hf,7.0,Base,1.954
2.025,2.12,1.7,1.58,2.158,2.014,1.8,1.275,,Qwen/Qwen1.5-0.5B,0.5,Base,1.834
1.762,1.8,1.443,1.33,1.947,2.188,1.59,1.125,,allenai/OLMo-1B,1.0,Base,1.648
1.288,1.45,1.471,1.25,1.908,1.667,1.38,1.162,1.129,CohereForAI/aya-101,13.0,Chat,1.447
1.325,1.49,1.186,1.34,1.579,2.159,1.2,1.012,,google/gemma-7b,7.0,Base,1.411
1.112,1.01,1.0,1.0,1.434,1.507,1.0,1.012,,microsoft/phi-1,1.3,Base,1.135