AI AgriBench Post-Cutoff
Models answer 146 questions from newer agricultural extension documents. Judges score their answers for accuracy, relevance, completeness and conciseness.
Seven configurations have scores on the subset. All 146 question IDs also appear in the 416-question test.
- Released
- January 2026
- Kind
- Tasks from real jobs
- Level
- University
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- New versions replace it
- Run by
- A host
- Based on
- AI AgriBench
- Strongest model tested
-
Gemini 3 Pro #56 on the capability index
- Last model added
- November 2025
- Scores refreshed
- November 20th, 2026
GPT-5 leads with 98.1 among models released by November 2025
Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.
The newest model with a score here came out in November 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1 GPT-5 98.1
- 2 GPT-5.1 97.7
- 3 GPT-5 mini 95.9
- 4
Gemini 3 Pro 94.8
- 5 Claude Opus 4.1 94.2
- 6
DeepSeek-V3 Mar 2025 91.0
- 7
Qwen2.5-72B 84.9
Source: Official AI AgriBench Post-Cutoff leaderboard
| # | Model | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | GPT-5 | 98.1 | Aug 2025 | Dec 2025 | Official leaderboard | |
| 2 | GPT-5.1 | 97.7 | Nov 2025 | Dec 2025 | Official leaderboard | |
| 3 | GPT-5 mini | 95.9 | Aug 2025 | Dec 2025 | Official leaderboard | |
| 4 | | 94.8 | Nov 2025 | Dec 2025 | Official leaderboard | |
| 5 | Claude Opus 4.1 | 94.2 | Aug 2025 | Dec 2025 | Official leaderboard | |
| 6 | | 91.0 | Mar 2025 | Dec 2025 | Official leaderboard | |
| 7 | | 84.9 | Sep 2024 | Dec 2025 | Official leaderboard |
Rankings by part
We read 9 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Pests and Pest Management, Diseases and Disease Management and Weeds and Weed Management. GPT-5 leads 8 of them, and GPT-5.1 leads the other one. Arrows show how far a model moved from its overall rank among the models we track.
Pests and Pest Management
7 models we track have a score here.
- 1 GPT-5 98.7
- 2 GPT-5.1 97.4
- 3 Claude Opus 4.1 ↑2 96.7
- 4 GPT-5 mini ↓1 96.4
- 5
Gemini 3 Pro ↓1 95.7
- 6
DeepSeek-V3 Mar 2025 92.2
- 7
Qwen2.5-72B 86.6
Diseases and Disease Management
7 models we track have a score here.
- 1 GPT-5 100.0
- 2 GPT-5 mini ↑1 100.0
- 3 GPT-5.1 ↓1 98.8
- 4 Claude Opus 4.1 ↑1 97.9
- 5
Gemini 3 Pro ↓1 97.6
- 6
DeepSeek-V3 Mar 2025 94.0
- 7
Qwen2.5-72B 87.5
Weeds and Weed Management
7 models we track have a score here.
- 1 GPT-5.1 ↑1 97.4
- 2 GPT-5 ↓1 97.2
- 3 GPT-5 mini 95.6
- 4
Gemini 3 Pro 94.7
- 5 Claude Opus 4.1 91.7
- 6
DeepSeek-V3 Mar 2025 88.4
- 7
Qwen2.5-72B 80.5
Crop Nutrition and Fertility Management
7 models we track have a score here.
- 1 GPT-5 98.1
- 2 GPT-5.1 96.9
- 3 GPT-5 mini 95.5
- 4 Claude Opus 4.1 ↑1 94.6
- 5
DeepSeek-V3 Mar 2025 ↑1 92.8
- 6
Gemini 3 Pro ↓2 92.4
- 7
Qwen2.5-72B 83.7
Soils and Soil Health
7 models we track have a score here.
- 1 GPT-5 99.7
- 2 GPT-5.1 99.5
- 3 GPT-5 mini 99.4
- 4 Claude Opus 4.1 ↑1 97.8
- 5
DeepSeek-V3 Mar 2025 ↑1 97.2
- 6
Gemini 3 Pro ↓2 96.6
- 7
Qwen2.5-72B 92.6
Horticultural and Agronomic Practices
7 models we track have a score here.
- 1 GPT-5 99.5
- 2 GPT-5.1 98.5
- 3 Claude Opus 4.1 ↑2 96.6
- 4 GPT-5 mini ↓1 96.4
- 5
Gemini 3 Pro ↓1 95.7
- 6
DeepSeek-V3 Mar 2025 94.6
- 7
Qwen2.5-72B 89.5
Seed Hybrid Rootstock Selection
7 models we track have a score here.
- 1 GPT-5 99.4
- 2 GPT-5.1 99.4
- 3 GPT-5 mini 98.9
- 4 Claude Opus 4.1 ↑1 98.3
- 5
Gemini 3 Pro ↓1 97.8
- 6
DeepSeek-V3 Mar 2025 96.7
- 7
Qwen2.5-72B 90.6
Weather and Weather Risks
7 models we track have a score here.
- 1 GPT-5 99.4
- 2 GPT-5 mini ↑1 98.3
- 3 GPT-5.1 ↓1 98.3
- 4 Claude Opus 4.1 ↑1 97.2
- 5
Gemini 3 Pro ↓1 94.4
- 6
DeepSeek-V3 Mar 2025 93.3
- 7
Qwen2.5-72B 87.2
Water Management and Irrigation
7 models we track have a score here.
- 1 GPT-5 99.1
- 2 GPT-5 mini ↑1 98.2
- 3 GPT-5.1 ↓1 96.9
- 4 Claude Opus 4.1 ↑1 94.5
- 5
Gemini 3 Pro ↓1 93.5
- 6
DeepSeek-V3 Mar 2025 92.6
- 7
Qwen2.5-72B 85.2
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official AI AgriBench Post-Cutoff leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official AI AgriBench Post-Cutoff leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
Versions
More in Economic work
- JobBench In use 130 tasks from 35 occupations workers most want delegated. Agent works through messy reference files, graded by fact-anchored binary rubrics. GLM-5.3 61.4%
- GDPval In use Real work tasks from 44 occupations with reference files. Experts blindly compare model deliverables with expert work. Metric is win-or-tie rate.
Seed2.1 Pro 87.9%
- GDPval-AA v2.1 In use Agents with shell and web access complete 220 GDPval gold tasks from 44 occupations. Blind pairwise comparisons give Elo ratings. Claude Opus 5.5 1,846
- AA-Briefcase v1.1 In use Version 1.1 of Artificial Analysis's multi-hour office work evaluation, with Elo ratings fitted by Crowd-BT. Claude Opus 5.5 1,822
- Agents' Last Exam v1.1 In use Agents complete 122 public long-horizon professional workflow tasks across 55 sub-industries. Deterministic graders check outcomes against hidden references. GPT-6.2 Astra 47.5%
- CoWorkBench In use Agent completes long-horizon productivity tasks across computer science, finance, law and medicine. Qwen in-house scoring (method unpublished). Claude Fable 5 75.9%
Data audit
All 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access Public tasks, plus a private test set.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the official leaderboard (7 entries).
- Pass Models scored 7 models we track.
- Note Newest score The newest came 12 months ago, in November 2025, for Gemini 3 Pro. That’s expected for a test replaced by AI AgriBench.
- Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is Gemini 3 Pro (#56).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on aiagribench.org: 7 rows for models we track at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.