Benchmark Almanac

AgroBench

GPT-4o Aug 2024 73.5% leads since July 2025
Not in model cards

Models answer illustrated questions from agronomists about crops, diseases, pests, weeds, machinery and farming practices. The overall score averages accuracy across seven tasks.

The authors include 682 crop and disease combinations, 134 pest categories and 108 weed categories.

Made by
Risa Shinoda and colleagues
Released
July 2025
Kind
General visual questions
Level
University
Scored
Checked automatically
Answers
Multiple choice
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Images → Text
Interaction
Single turn
Items from
Written by experts
Refresh
One fixed set
Run by
Anyone
In views
Vision
Strongest model tested
GPT-4o Aug 2024 #167 on the capability index
Last model added
August 2024
Scores refreshed
November 20th, 2026
12
Entries in its paper, 9 models we track

GPT-4o leads with 73.5% among models released by August 2024 GPT-4o leads with 73.5% among models released by August 2024

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. 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. This view shows only models we track, each at its best.

The newest model with a score here came out in August 2024, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 GPT-4o Aug 2024, With images 73.5%
  2. 2 Gemini 1.5 Pro May 2024, With images 72.2%
  3. 3 QwenVLM-72B With images 70.7%
  4. 4 Gemini 1.5 Flash May 2024, With images 67.5%
  5. 5 QwenVLM-7B With images 64.2%
  6. 6 GPT-4o mini With images 62.1%
  7. 7 LLaVA-NeXT-72B With images 59.3%
  8. 8 llama3-llava-next-8b With images 51.3%
  9. 9 CogVLM-19B With images 50.4%
  10. 10 LLaVA-v1.5-13B With images 50%
  11. 11 llava-v1.5-7b With images 45.4%
  12. 12 Emu2-Chat With images 40.5%

Source: The AgroBench paper

#EntryScoreSettingDateSource
1 GPT-4o Aug 2024 73.5% With images Aug 2024 Official leaderboard
2 Gemini 1.5 Pro May 2024 72.2% With images May 2024 Official leaderboard
3 QwenVLM-72B 70.7% With images Official leaderboard
4 Gemini 1.5 Flash May 2024 67.5% With images May 2024 Official leaderboard
5 QwenVLM-7B 64.2% With images Official leaderboard
6 GPT-4o mini 62.1% With images Jul 2024 Official leaderboard
7 LLaVA-NeXT-72B 59.3% With images May 2024 Official leaderboard
8 llama3-llava-next-8b 51.3% With images Apr 2024 Official leaderboard
9 CogVLM-19B 50.4% With images Official leaderboard
10 LLaVA-v1.5-13B 50% With images Oct 2023 Official leaderboard
11 llava-v1.5-7b 45.4% With images Oct 2023 Official leaderboard
12 Emu2-Chat 40.5% With images Dec 2023 Official leaderboard
#ModelScoreSettingDateSource
1 GPT-4o Aug 2024 73.5% With images Aug 2024 Official leaderboard
2 Gemini 1.5 Pro May 2024 72.2% With images May 2024 Official leaderboard
3 Gemini 1.5 Flash May 2024 67.5% With images May 2024 Official leaderboard
4 GPT-4o mini 62.1% With images Jul 2024 Official leaderboard
5 LLaVA-NeXT-72B 59.3% With images May 2024 Official leaderboard
6 llama3-llava-next-8b 51.3% With images Apr 2024 Official leaderboard
7 LLaVA-v1.5-13B 50% With images Oct 2023 Official leaderboard
8 llava-v1.5-7b 45.4% With images Oct 2023 Official leaderboard
9 Emu2-Chat 40.5% With images Dec 2023 Official leaderboard

Rankings by part

We read 7 parts from the benchmark’s paper, each ranking models on one part of the test, such as Disease identification, Disease management and Pest identification. GPT-4o leads 5 of them, and Gemini 1.5 Pro leads the other 2. Arrows show how far a model moved from its overall rank among the models we track.

Disease identification

9 models we track have a score here.

  1. 1 GPT-4o Aug 2024 64.2%
  2. 2 Gemini 1.5 Pro May 2024 62.9%
  3. 3 Gemini 1.5 Flash May 2024 55.1%
  4. 4 LLaVA-NeXT-72B ↑1 55%
  5. 5 GPT-4o mini ↓1 53.6%
  6. 6 llama3-llava-next-8b 45.5%
  7. 7 Emu2-Chat ↑2 42%
  8. 8 LLaVA-v1.5-13B ↓1 40.2%
  9. 9 llava-v1.5-7b ↓1 36%

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI
Benchmark paper Not tested since Jul 2025
GPT-4o 73.5%

Source: The AgroBench paper

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
In the benchmark’s paper Best so far
0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) GPT-4o Gemini 1.5 Pro LLaVA-NeXT-72B llama3-llava-next-8b LLaVA-v1.5-13B 0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) GPT-4o LLaVA-NeXT-72B

Source: Official AgroBench 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 Vision

All 636 in Vision
  • MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy. Qwen 3.6 Plus 86%
  • MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
  • CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
  • MathVista In use Math reasoning in visual contexts (charts, geometry, puzzles) from 31 datasets. Answer accuracy. Seed2.1 Pro 90.7%
  • MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy. Qwen 3.8 Max 97.7%
  • MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy. Qwen 3.8 Max 85.9%

Data audit

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in August 2024, for GPT-4o. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
  • Pass Independent runs Scores from the benchmark’s paper (12 entries).
  • Pass Models scored 9 models we track, plus 3 other entries on its leaderboard.
  • Warning Newest score The newest came 2 years ago, in August 2024, for GPT-4o.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-4o (#167).
  • Pass Headroom The best is 73.5%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 11 rows for models we track and 3 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