| model_name,ag_input_researcher,large_farm_operator,professional_farmer,small_farmer,Average (All Topics) | |
| Claude-3.5-haiku,82.5566,135.9821,39.3398,34.8821,73.1902 | |
| Claude-haiku-4.5,505.3357,429.9719,428.2429,97.9653,365.379 | |
| Claude-opus-4.5,262.264,287.1955,218.8891,184.0394,238.097 | |
| Claude-sonnet-4.5,303.1843,327.0878,414.7977,88.6822,283.438 | |
| DeepSeek-R1-0528,140.1887,169.6385,128.3669,198.5396,159.1834 | |
| Deepseek-v3.1,183.559,139.6033,187.8543,111.7123,155.6822 | |
| Deepseek-v3.2-exp,244.6648,406.296,299.7771,574.8698,381.4019 | |
| DeepSeek-V3-0324,138.0578,103.0631,61.6246,99.771,100.6291 | |
| Gemini-2.5-flash,74.7668,114.7857,52.9284,117.9559,90.1092 | |
| Gemini-2.5-flash-lite,46.7497,126.2675,78.7248,67.6446,79.8466 | |
| Gemini-2.5-pro,111.8302,211.7131,333.2687,90.8846,186.9242 | |
| Gemini-3-pro-preview,85.0926,226.4012,123.7004,136.8691,143.0158 | |
| Gemma-3-27b-it,125.7667,143.5144,98.4628,78.5559,111.575 | |
| GLM-4.5,177.9138,268.271,156.8146,199.9109,200.7276 | |
| GLM-4.5-Air,133.3058,203.0477,111.3307,129.7452,144.3573 | |
| Gpt-5,270.6952,231.2776,460.3306,287.0378,312.3353 | |
| Gpt-5.1,258.928,421.9474,310.7583,398.995,347.6572 | |
| Gpt-5-mini,178.0177,200.8393,382.6333,135.2867,224.1943 | |
| Gpt-oss-120b,93.7805,232.8232,156.9678,126.4374,152.5022 | |
| Grok-3-mini,111.2626,95.6699,49.413,131.7218,97.0168 | |
| Grok-4,207.0462,201.0777,248.9985,222.3432,219.8664 | |
| Grok-4.1-fast,76.1989,50.1805,81.6435,51.9029,64.9814 | |
| Grok-4.1-fast-thinking,141.7984,183.0821,124.9736,257.7874,176.9104 | |
| Kimi-K2-Instruct,126.4835,101.5517,58.2718,59.561,86.467 | |
| Kimi-k2-thinking,295.3688,424.5914,404.3292,316.7339,360.2558 | |
| Llama-3.1-nemotron-ultra-253b-v1,77.4809,264.0078,111.0316,196.0713,162.1479 | |
| Llama-3.3-nemotron-super-49b-v1.5,144.0573,190.3735,157.552,172.3549,166.0844 | |
| Llama-4-maverick,46.0676,79.7149,42.1974,93.3224,65.3256 | |
| Llama-4-scout,84.3751,50.6148,64.8301,40.7168,60.1342 | |
| Magistral-small-2506,54.7524,39.98,40.8038,90.1499,56.4215 | |
| Minimax-m2,235.9933,245.0915,306.1565,166.9771,238.5546 | |
| Mistral-large-2512,172.1075,172.686,100.2139,127.0358,143.0108 | |
| Nemotron-nano-9b-v2,113.5692,74.4862,108.4956,59.4245,88.9939 | |
| Nova-lite-v1,46.3406,40.7874,44.4915,35.3865,41.7515 | |
| Nova-pro-v1,59.3802,45.6604,38.874,39.8618,45.9441 | |
| Phi-3-mini-128k-instruct,63.87,192.8367,201.1701,113.9741,142.9627 | |
| Phi-4,45.1202,48.9424,37.5591,108.0087,59.9076 | |
| Qwen3-235B-A22B-Thinking-2507,190.5779,230.2108,179.2427,418.9615,254.7482 | |
| Qwen3-30b-a3b-instruct-2507,138.3152,134.0822,368.9601,56.5183,174.469 | |
| Qwen3-next-80b-a3b-thinking,87.0402,165.2689,106.1542,149.1552,126.9046 | |