AI AgriBench Smallholders
Models answer questions that smallholder farmers sent to advisory services. A judge scores the responses against answers from the advisors.
The public table scores 13 configurations. Eleven have 3,434 distinct question IDs each. The two Shennong configurations have 3,442 and 3,443.
- Kind
- Tasks from real jobs
- Level
- University
- Scored
- Graded by a model
- Answers
- Open-ended
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- A host
- Occupations
- Farming, fishing and forestry
- Strongest model tested
-
Gemini 3 Pro #56 on the capability index
- Last model added
- November 2025
- Scores refreshed
- November 20th, 2026
shennong-3.0-professional tops the leaderboard with 84.0 GPT-5 mini leads with 80.9 among models released by November 2025
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is GPT-5 mini, at 80.9. This view shows only models we track, each at 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 shennong-3.0-professional 84.0
- 2 GPT-5 mini 80.9
- 3 GPT-5.1 80.8
- 4 shennong-3.0-concise 79.2
- 5 Kimi K2 Thinking 78.2
- 6
Gemini 3 Pro 77.0
- 7 gpt-oss-120b 75.8
- 8 gpt-oss-20b 67.5
- 9
Llama 3.3 70B Instruct 65.4
- 10 digital-green-bot 61.7
- 11 agrillm/llama-3.3-70b-instruct (with-rag) 60.8
- 12
Qwen3-30B-A3B 58.8
Source: Official AI AgriBench Smallholders leaderboard
- 1 GPT-5 mini 80.9
- 2 GPT-5.1 80.8
- 3 Kimi K2 Thinking 78.2
- 4
Gemini 3 Pro 77.0
- 5 gpt-oss-120b 75.8
- 6 gpt-oss-20b 67.5
- 7
Llama 3.3 70B Instruct 65.4
- 8
Qwen3-30B-A3B 58.8
Source: Official AI AgriBench Smallholders leaderboard
| # | Entry | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | shennong-3.0-professional | 84.0 | Feb 2026 | Official leaderboard | ||
| 2 | GPT-5 mini | 80.9 | Aug 2025 | Dec 2025 | Official leaderboard | |
| 3 | GPT-5.1 | 80.8 | Nov 2025 | Dec 2025 | Official leaderboard | |
| 4 | shennong-3.0-concise | 79.2 | Feb 2026 | Official leaderboard | ||
| 5 | Kimi K2 Thinking | 78.2 | Nov 2025 | Dec 2025 | Official leaderboard | |
| 6 | | 77.0 | Nov 2025 | Dec 2025 | Official leaderboard | |
| 7 | gpt-oss-120b | 75.8 | Aug 2025 | Dec 2025 | Official leaderboard | |
| 8 | gpt-oss-20b | 67.5 | Aug 2025 | Dec 2025 | Official leaderboard | |
| 9 | | 65.4 | Dec 2024 | Dec 2025 | Official leaderboard | |
| 10 | digital-green-bot | 61.7 | Dec 2025 | Official leaderboard | ||
| 11 | agrillm/llama-3.3-70b-instruct (with-rag) | 60.8 | Dec 2025 | Official leaderboard | ||
| 12 | | 58.8 | Apr 2025 | Dec 2025 | Official leaderboard |
| # | Model | Score | Setting | Released | Run on | Source |
|---|---|---|---|---|---|---|
| 1 | GPT-5 mini | 80.9 | Aug 2025 | Dec 2025 | Official leaderboard | |
| 2 | GPT-5.1 | 80.8 | Nov 2025 | Dec 2025 | Official leaderboard | |
| 3 | Kimi K2 Thinking | 78.2 | Nov 2025 | Dec 2025 | Official leaderboard | |
| 4 | | 77.0 | Nov 2025 | Dec 2025 | Official leaderboard | |
| 5 | gpt-oss-120b | 75.8 | Aug 2025 | Dec 2025 | Official leaderboard | |
| 6 | gpt-oss-20b | 67.5 | Aug 2025 | Dec 2025 | Official leaderboard | |
| 7 | | 65.4 | Dec 2024 | Dec 2025 | Official leaderboard | |
| 8 | | 58.8 | Apr 2025 | 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 Nutrition & fertility, Diseases and Other agronomic. GPT-5 mini leads 6 of them, and GPT-5.1 leads the other 3. Arrows show how far a model moved from its overall rank among the models we track.
Nutrition & fertility
8 models we track have a score here.
- 1 GPT-5 mini 81.9
- 2 GPT-5.1 80.4
- 3 gpt-oss-120b ↑2 79.0
- 4 Kimi K2 Thinking ↓1 78.5
- 5
Gemini 3 Pro ↓1 76.3
- 6 gpt-oss-20b 69.7
- 7
Llama 3.3 70B Instruct 66.0
- 8
Qwen3-30B-A3B 59.4
Diseases
8 models we track have a score here.
- 1 GPT-5 mini 83.4
- 2 GPT-5.1 83.2
- 3 Kimi K2 Thinking 81.5
- 4 gpt-oss-120b ↑1 79.2
- 5
Gemini 3 Pro ↓1 78.7
- 6 gpt-oss-20b 67.2
- 7
Llama 3.3 70B Instruct 66.9
- 8
Qwen3-30B-A3B 60.9
Other agronomic
8 models we track have a score here.
- 1 GPT-5.1 ↑1 81.5
- 2 GPT-5 mini ↓1 81.5
- 3 Kimi K2 Thinking 77.9
- 4
Gemini 3 Pro 77.5
- 5 gpt-oss-120b 77.1
- 6 gpt-oss-20b 71.0
- 7
Llama 3.3 70B Instruct 66.1
- 8
Qwen3-30B-A3B 59.2
Pests
8 models we track have a score here.
- 1 GPT-5.1 ↑1 82.2
- 2 GPT-5 mini ↓1 81.9
- 3 Kimi K2 Thinking 80.0
- 4
Gemini 3 Pro 77.7
- 5 gpt-oss-120b 74.4
- 6
Llama 3.3 70B Instruct ↑1 66.0
- 7 gpt-oss-20b ↓1 65.9
- 8
Qwen3-30B-A3B 60.6
Seed / hybrid / rootstock
8 models we track have a score here.
- 1 GPT-5 mini 75.9
- 2 GPT-5.1 75.8
- 3 Kimi K2 Thinking 74.5
- 4
Gemini 3 Pro 74.1
- 5 gpt-oss-120b 70.4
- 6
Llama 3.3 70B Instruct ↑1 61.3
- 7 gpt-oss-20b ↓1 59.2
- 8
Qwen3-30B-A3B 54.0
Soils
8 models we track have a score here.
- 1 GPT-5 mini 83.1
- 2 GPT-5.1 82.3
- 3 Kimi K2 Thinking 80.3
- 4 gpt-oss-120b ↑1 79.9
- 5
Gemini 3 Pro ↓1 77.3
- 6 gpt-oss-20b 71.5
- 7
Llama 3.3 70B Instruct 67.6
- 8
Qwen3-30B-A3B 61.3
Water
8 models we track have a score here.
- 1 GPT-5 mini 82.3
- 2 GPT-5.1 82.0
- 3 Kimi K2 Thinking 80.6
- 4 gpt-oss-120b ↑1 79.6
- 5
Gemini 3 Pro ↓1 77.2
- 6 gpt-oss-20b 70.1
- 7
Llama 3.3 70B Instruct 66.5
- 8
Qwen3-30B-A3B 60.5
Weather
8 models we track have a score here.
- 1 GPT-5 mini 79.9
- 2 GPT-5.1 79.5
- 3 Kimi K2 Thinking 76.9
- 4 gpt-oss-120b ↑1 76.1
- 5
Gemini 3 Pro ↓1 75.6
- 6 gpt-oss-20b 70.9
- 7
Llama 3.3 70B Instruct 66.2
- 8
Qwen3-30B-A3B 57.0
Weeds
8 models we track have a score here.
- 1 GPT-5.1 ↑1 80.6
- 2 GPT-5 mini ↓1 78.4
- 3
Gemini 3 Pro ↑1 78.0
- 4 Kimi K2 Thinking ↓1 77.9
- 5 gpt-oss-120b 68.0
- 6
Llama 3.3 70B Instruct ↑1 63.6
- 7
Qwen3-30B-A3B ↑1 58.9
- 8 gpt-oss-20b ↓2 57.6
3 models have held number one on the official leaderboard since 2023
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official AI AgriBench Smallholders 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 Smallholders 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.
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
7 of 9 checks pass, 2 warnings. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark
Catalog record 1 warning 1 pass
- Warning Task access We don’t know whether the tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (12 entries).
- Pass Models scored 8 models we track, plus 4 other entries on its leaderboard.
- Warning Newest score The newest came 12 months ago, in November 2025, for Gemini 3 Pro.
- Note Frontier models None of the top 10 has a score. 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: 9 rows for models we track and 4 other entries 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.