PeterKruger's picture
Upload 7 files
11b5f6a verified
model_name,ag_input_researcher,large_farm_operator,professional_farmer,small_farmer,Average (All Topics)
Claude-3.5-haiku,0.00720051,0.00668192,0.00667434,0.0061498,0.006715112
Claude-haiku-4.5,0.02489296,0.02013418,0.01843746,0.01245574,0.019457209
Claude-opus-4.5,0.07110321,0.08098408,0.07469458,0.06461012,0.073115232
Claude-sonnet-4.5,0.024281,0.02470702,0.02045244,0.01217264,0.02082266
DeepSeek-R1-0528,0.00286639,0.0029719,0.00259405,0.0037869,0.003029674
Deepseek-v3.1,0.0009926,0.00103477,0.00089927,0.00086981,0.00095418
Deepseek-v3.2-exp,0.00066938,0.00082639,0.00067067,0.00099708,0.000778611
DeepSeek-V3-0324,0.00071608,0.00069401,0.000633,0.00059477,0.000664179
Gemini-2.5-flash,0.00423233,0.00520907,0.00395669,0.00375983,0.004311835
Gemini-2.5-flash-lite,0.00063077,0.00079674,0.00059305,0.00064157,0.000663739
Gemini-2.5-pro,0.03930419,0.04171929,0.03866309,0.03824411,0.039532906
Gemini-3-pro-preview,0.035101,0.04412368,0.03692442,0.03940919,0.038810289
Gemma-3-27b-it,0.00034033,0.00033513,0.00031045,0.00027395,0.00031739
GLM-4.5,0.00334257,0.0034681,0.00302012,0.00362297,0.003354639
GLM-4.5-Air,0.00171533,0.00164344,0.00145099,0.00134833,0.00155505
Gpt-5,0.05574779,0.05762194,0.05242862,0.05094797,0.054344102
Gpt-5.1,0.07600665,0.08595698,0.07228595,0.07323105,0.076993304
Gpt-5-mini,0.00837425,0.00861073,0.0082708,0.00703315,0.008105237
Gpt-oss-120b,0.00074131,0.00078443,0.00067502,0.0006203,0.000710107
Grok-3-mini,0.00093854,0.00100777,0.00094697,0.0009729,0.000965325
Grok-4,0.03467529,0.03134831,0.03279726,0.03809512,0.034134457
Grok-4.1-fast,0.00078635,0.00076243,0.00076237,0.00068448,0.000752717
Grok-4.1-fast-thinking,0.00076111,0.00074955,0.00076133,0.00066767,0.000738308
Kimi-K2-Instruct,0.00219623,0.00243434,0.00206643,0.00159412,0.002095738
Kimi-k2-thinking,0.00663416,0.00905259,0.00863894,0.00805154,0.008030023
Llama-3.1-nemotron-ultra-253b-v1,0.00184655,0.00212877,0.00191439,0.00241326,0.002052804
Llama-3.3-nemotron-super-49b-v1.5,0.00096714,0.00123108,0.00112008,0.00132855,0.001149371
Llama-4-maverick,0.00047313,0.00047299,0.00044071,0.00047342,0.00046525
Llama-4-scout,0.00023322,0.00025136,0.00023453,0.00021578,0.0002344
Magistral-small-2506,0.00103903,0.00113252,0.00097848,0.00087559,0.001012177
Minimax-m2,0.0038598,0.00330771,0.00424363,0.00273631,0.003582245
Mistral-large-2512,0.00352451,0.00354138,0.00324105,0.00268537,0.003281909
Nemotron-nano-9b-v2,0.0002837,0.00027182,0.00022324,0.00022866,0.000254074
Nova-lite-v1,0.00017192,0.00018757,0.0001659,0.00017551,0.00017519
Nova-pro-v1,0.00164883,0.00169965,0.00149093,0.00141377,0.001572756
Phi-3-mini-128k-instruct,0.00021982,0.00028748,0.00026441,0.0001653,0.000235708
Phi-4,0.00009619,0.00009927,0.00008531,0.0000851,9.1938E-05
Qwen3-235B-A22B-Thinking-2507,0.00130406,0.00134382,0.00139143,0.00130582,0.001336043
Qwen3-30b-a3b-instruct-2507,0.00035343,0.00040343,0.00033623,0.00028744,0.000347808
Qwen3-next-80b-a3b-thinking,0.00353934,0.00452363,0.00420806,0.00398458,0.004047989