Benchmark Almanac

AI AgriBench Smallholders

shennong-3.0-professional 84.0 tops its leaderboard GPT-5 mini 80.9 leads the models we track
Not in model cards

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
In and out
Text → Text
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
12
Entries on its own leaderboard, 8 models we track

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:

  1. 1 shennong-3.0-professional 84.0
  2. 2 GPT-5 mini 80.9
  3. 3 GPT-5.1 80.8
  4. 4 shennong-3.0-concise 79.2
  5. 5 Kimi K2 Thinking 78.2
  6. 6 Gemini 3 Pro 77.0
  7. 7 gpt-oss-120b 75.8
  8. 8 gpt-oss-20b 67.5
  9. 9 Llama 3.3 70B Instruct 65.4
  10. 10 digital-green-bot 61.7
  11. 11 agrillm/llama-3.3-70b-instruct (with-rag) 60.8
  12. 12 Qwen3-30B-A3B 58.8

Source: Official AI AgriBench Smallholders leaderboard

#EntryScoreSettingReleasedRun onSource
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 Gemini 3 Pro 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 Llama 3.3 70B Instruct 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 Qwen3-30B-A3B 58.8 Apr 2025 Dec 2025 Official leaderboard
#ModelScoreSettingReleasedRun onSource
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 Gemini 3 Pro 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 Llama 3.3 70B Instruct 65.4 Dec 2024 Dec 2025 Official leaderboard
8 Qwen3-30B-A3B 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. 1 GPT-5 mini 81.9
  2. 2 GPT-5.1 80.4
  3. 3 gpt-oss-120b ↑2 79.0
  4. 4 Kimi K2 Thinking ↓1 78.5
  5. 5 Gemini 3 Pro ↓1 76.3
  6. 6 gpt-oss-20b 69.7
  7. 7 Llama 3.3 70B Instruct 66.0
  8. 8 Qwen3-30B-A3B 59.4

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.

Meta OpenAI
Own leaderboard Not tested since Nov 2025
GPT-5 mini 80.9

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.

Plot with other benchmarks
On the benchmark’s own leaderboard
60.0 70.0 80.0 2025 2026 60.0 70.0 80.0 2025 2026

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

All 210 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.

How we check