AgroBench
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
- 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
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:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1 GPT-4o Aug 2024, With images 73.5%
- 2
Gemini 1.5 Pro May 2024, With images 72.2%
- 3 QwenVLM-72B With images 70.7%
- 4
Gemini 1.5 Flash May 2024, With images 67.5%
- 5 QwenVLM-7B With images 64.2%
- 6 GPT-4o mini With images 62.1%
- 7
LLaVA-NeXT-72B With images 59.3%
- 8 llama3-llava-next-8b With images 51.3%
- 9 CogVLM-19B With images 50.4%
- 10
LLaVA-v1.5-13B With images 50%
- 11 llava-v1.5-7b With images 45.4%
- 12 Emu2-Chat With images 40.5%
Source: The AgroBench paper
- 1 GPT-4o Aug 2024, With images 73.5%
- 2
Gemini 1.5 Pro May 2024, With images 72.2%
- 3
Gemini 1.5 Flash May 2024, With images 67.5%
- 4 GPT-4o mini With images 62.1%
- 5
LLaVA-NeXT-72B With images 59.3%
- 6 llama3-llava-next-8b With images 51.3%
- 7
LLaVA-v1.5-13B With images 50%
- 8 llava-v1.5-7b With images 45.4%
- 9 Emu2-Chat With images 40.5%
Source: The AgroBench paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4o Aug 2024 | 73.5% | With images | Aug 2024 | Official leaderboard |
| 2 | | 72.2% | With images | May 2024 | Official leaderboard |
| 3 | QwenVLM-72B | 70.7% | With images | Official leaderboard | |
| 4 | | 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 | | 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 | | 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 |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4o Aug 2024 | 73.5% | With images | Aug 2024 | Official leaderboard |
| 2 | | 72.2% | With images | May 2024 | Official leaderboard |
| 3 | | 67.5% | With images | May 2024 | Official leaderboard |
| 4 | GPT-4o mini | 62.1% | With images | Jul 2024 | Official leaderboard |
| 5 | | 59.3% | With images | May 2024 | Official leaderboard |
| 6 | llama3-llava-next-8b | 51.3% | With images | Apr 2024 | Official leaderboard |
| 7 | | 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 GPT-4o Aug 2024 64.2%
- 2
Gemini 1.5 Pro May 2024 62.9%
- 3
Gemini 1.5 Flash May 2024 55.1%
- 4
LLaVA-NeXT-72B ↑1 55%
- 5 GPT-4o mini ↓1 53.6%
- 6 llama3-llava-next-8b 45.5%
- 7 Emu2-Chat ↑2 42%
- 8
LLaVA-v1.5-13B ↓1 40.2%
- 9 llava-v1.5-7b ↓1 36%
Disease management
9 models we track have a score here.
- 1 GPT-4o Aug 2024 87.3%
- 2
Gemini 1.5 Pro May 2024 81.5%
- 3 GPT-4o mini ↑1 80.7%
- 4
LLaVA-NeXT-72B ↑1 80%
- 5
Gemini 1.5 Flash May 2024 ↓2 80%
- 6 llama3-llava-next-8b 72.6%
- 7
LLaVA-v1.5-13B 68.9%
- 8 llava-v1.5-7b 62.7%
- 9 Emu2-Chat 48.3%
Pest identification
9 models we track have a score here.
- 1 GPT-4o Aug 2024 77.8%
- 2
Gemini 1.5 Pro May 2024 74.5%
- 3
Gemini 1.5 Flash May 2024 70%
- 4 GPT-4o mini 60%
- 5
LLaVA-NeXT-72B 49.8%
- 6
LLaVA-v1.5-13B ↑1 44.5%
- 7 Emu2-Chat ↑2 43.8%
- 8 llama3-llava-next-8b ↓2 43%
- 9 llava-v1.5-7b ↓1 38.8%
Weed identification
9 models we track have a score here.
- 1
Gemini 1.5 Pro May 2024 ↑1 55.2%
- 2
Gemini 1.5 Flash May 2024 ↑1 50.9%
- 3 GPT-4o Aug 2024 ↓2 44.2%
- 4 GPT-4o mini 35.1%
- 5 llama3-llava-next-8b ↑1 30.1%
- 6
LLaVA-NeXT-72B ↓1 27%
- 7
LLaVA-v1.5-13B 24.8%
- 8 llava-v1.5-7b 24.8%
- 9 Emu2-Chat 23.8%
Crop management
9 models we track have a score here.
- 1 GPT-4o Aug 2024 75.4%
- 2
Gemini 1.5 Pro May 2024 71%
- 3
LLaVA-NeXT-72B ↑2 66.9%
- 4
Gemini 1.5 Flash May 2024 ↓1 64.7%
- 5 GPT-4o mini ↓1 64.2%
- 6
LLaVA-v1.5-13B ↑1 59.4%
- 7 llama3-llava-next-8b ↓1 54.3%
- 8 llava-v1.5-7b 53.8%
- 9 Emu2-Chat 40.4%
Machine QA
9 models we track have a score here.
- 1
Gemini 1.5 Pro May 2024 ↑1 82.8%
- 2 GPT-4o Aug 2024 ↓1 82.8%
- 3
Gemini 1.5 Flash May 2024 78.2%
- 4 GPT-4o mini 71%
- 5
LLaVA-NeXT-72B 66.1%
- 6 llama3-llava-next-8b 56.1%
- 7
LLaVA-v1.5-13B 54.1%
- 8 llava-v1.5-7b 46.5%
- 9 Emu2-Chat 37.6%
Traditional methods
9 models we track have a score here.
- 1 GPT-4o Aug 2024 82.4%
- 2
Gemini 1.5 Pro May 2024 77.7%
- 3
Gemini 1.5 Flash May 2024 73.3%
- 4
LLaVA-NeXT-72B ↑1 70.4%
- 5 GPT-4o mini ↓1 69.8%
- 6
LLaVA-v1.5-13B ↑1 58.4%
- 7 llama3-llava-next-8b ↓1 57.5%
- 8 llava-v1.5-7b 55.2%
- 9 Emu2-Chat 47.8%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
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.
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
- 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.