SeedBench (Seed Science)
Models answer questions, summarize passages and interpret research on rice breeding in Chinese and English. The 11 task types use accuracy, macro F1 or ROUGE-L.
AgriJev independently evaluated five choice and classification tasks. The creators evaluated 26 models on the published 2,264-question benchmark.
- Released
- December 2024
- Kind
- Science questions
- Level
- University
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
-
DeepSeek-V3 Mar 2025 #141 on the capability index
- Last model added
- March 2025
- Scores refreshed
- November 20th, 2026
DeepSeek-V3 leads with 68.4 among models released by March 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 March 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
DeepSeek-V3 Mar 2025 68.4
- 2 GPT-4 Jun 2023 67.9
- 3
Qwen2-72B 62.5
Source: Official SeedBench (Seed Science) leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 68.4 | Mar 2025 | Official leaderboard | |
| 2 | GPT-4 Jun 2023 | 67.9 | Jun 2023 | Official leaderboard | |
| 3 | | 62.5 | Jun 2024 | Official leaderboard |
Rankings by part
We read 11 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as QA-1, QA-2 and QA-3. DeepSeek-V3 leads 6 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.
QA-1
3 models we track have a score here.
- 1
DeepSeek-V3 Mar 2025 72.5
- 2 GPT-4 Jun 2023 60.5
- 3
Qwen2-72B 59.5
QA-2
3 models we track have a score here.
- 1
DeepSeek-V3 Mar 2025 79.8
- 2
Qwen2-72B ↑1 76.0
- 3 GPT-4 Jun 2023 ↓1 73.9
QA-3
3 models we track have a score here.
- 1
DeepSeek-V3 Mar 2025 29.3
- 2 GPT-4 Jun 2023 21.4
- 3
Qwen2-72B 19.6
QA-4
3 models we track have a score here.
- 1
DeepSeek-V3 Mar 2025 40.6
- 2 GPT-4 Jun 2023 36.1
- 3
Qwen2-72B 31.6
SUM-1
3 models we track have a score here.
- 1 GPT-4 Jun 2023 ↑1 58.7
- 2
DeepSeek-V3 Mar 2025 ↓1 48.1
- 3
Qwen2-72B 31.1
SUM-2
3 models we track have a score here.
- 1
Qwen2-72B ↑2 63.1
- 2 GPT-4 Jun 2023 62.9
- 3
DeepSeek-V3 Mar 2025 ↓2 54.7
RC-1
3 models we track have a score here.
- 1 GPT-4 Jun 2023 ↑1 100.0
- 2
DeepSeek-V3 Mar 2025 ↓1 100.0
- 3
Qwen2-72B 99.1
RC-2
3 models we track have a score here.
- 1
DeepSeek-V3 Mar 2025 97.2
- 2 GPT-4 Jun 2023 96.4
- 3
Qwen2-72B 94.2
RC-3
3 models we track have a score here.
- 1
DeepSeek-V3 Mar 2025 87.9
- 2 GPT-4 Jun 2023 87.9
- 3
Qwen2-72B 72.2
RC-4
3 models we track have a score here.
- 1 GPT-4 Jun 2023 ↑1 62.3
- 2
DeepSeek-V3 Mar 2025 ↓1 55.2
- 3
Qwen2-72B 51.6
RC-5
3 models we track have a score here.
- 1
Qwen2-72B ↑2 90.0
- 2 GPT-4 Jun 2023 86.7
- 3
DeepSeek-V3 Mar 2025 ↓2 86.7
2 models have held number one on the official leaderboard since its release in December 2024
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official SeedBench (Seed Science) 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 SeedBench (Seed Science) 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 Science and reasoning
- GPQA Diamond In use 198 graduate-level 'Google-proof' multiple-choice questions in biology, chemistry and physics.
Gemini 4 Carbon 97%
- Terminal-Bench-Science In use 70 scientific research-workflow tasks across five science areas, run in Harbor containers. Hidden tests give the resolution rate. GPT-6 Astra 68.1%
- BioMysteryBench In use Bioinformatics problems on anonymized real datasets that require real analysis with tools. Rubric-graded, with human-solvable and human-difficult splits. Claude Fable 5.2 83.7%
- FrontierScience In use Models solve physics, chemistry, and biology problems in an Olympiad track graded by short answer and a Research track graded by 10-point rubrics.
Intern-S2-397B 87%
- HiPhO In use Models solve theory problems from 2024 and 2025 physics olympiad exams, some with diagrams. Official marking schemes grade answers and steps, mapped to medal levels.
Gemini 3 Pro 78.3%
- LABBench2 In use 11 biology research sub-tasks (literature, figures, tables, patents, trials and more) with tool access. Macro-averaged accuracy. GPT-5.2 60.9%
Data audit
7 of 8 checks pass, 1 warning. Look first at the Newest score check. The newest came 20 months ago, in March 2025, for DeepSeek-V3. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 1 pass 3 notes
- Pass Independent runs Scores from the official leaderboard (3 entries).
- Note Models scored Only 3 models we track.
- Warning Newest score The newest came 20 months ago, in March 2025, for DeepSeek-V3.
- Note Frontier models None of the top 10 has a score. The strongest tested is DeepSeek-V3 (#141).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 3 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.