AstroCLIMB
Models compare pairs of astronomy figures or captions. They determine whether the pair shares a figure, shares a paper, comes from citation-linked papers, or comes from unrelated papers.
Ten teams published system papers. One team adapted Qwen3.5-4B and scored 0.751 macro F1 on the 10,000 test pairs.
- Released
- July 2026
- Kind
- Lab and data work
- Level
- University
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Subject
- Physical sciences
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- A host
- In views
- Vision
Gaelaw tops the leaderboard with 0.79
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.
- 0.79 Gaelaw
- 0.75 Irving Ernesto
- 0.74 HCMUS_Beyonders
- 0.74 AI_COE_Tredence
- 0.74 Syed Mohaiminul Hoque
- 0.69 Letus Pata
- 0.66 [Deleted] 85efbf09-6a44-42d0-a91b-f7dd9a3d8932
- 0.64 PSGS
- 0.61 AI Duo
- 0.49 Ethan Seefried
- 0.48 denza sikora
- 0.48 Global_Optima
- 0.46 shubham sharma1111111
- 0.45 amarzouyoussef
- 0.42 Truong Giang
- 0.41 bsenst
- 0.40 Steve K
- 0.25 sample_submission.csv
- 0.25 Himanshu Dhiman
- 1 Gaelaw 0.79
- 2 Irving Ernesto 0.75
- 3 HCMUS_Beyonders 0.74
- 4 AI_COE_Tredence 0.74
- 5 Syed Mohaiminul Hoque 0.74
- 6 Letus Pata 0.69
- 7 [Deleted] 85efbf09-6a44-42d0-a91b-f7dd9a3d8932 0.66
- 8 PSGS 0.64
- 9 AI Duo 0.61
- 10 Ethan Seefried 0.49
- 11 denza sikora 0.48
- 12 Global_Optima 0.48
- 13 shubham sharma1111111 0.46
- 14 amarzouyoussef 0.45
- 15 Truong Giang 0.42
- 16 bsenst 0.41
- 17 Steve K 0.40
- 18 sample_submission.csv 0.25
- 19 Himanshu Dhiman 0.25
Source: Official AstroCLIMB leaderboard
| # | Entry | Score | Setting | Submitted by | Date | Source |
|---|---|---|---|---|---|---|
| 1 | Gaelaw | 0.79 | Gaelaw | Oct 2026 | Official leaderboard | |
| 2 | Irving Ernesto | 0.75 | Irving Ernesto | Sep 2026 | Official leaderboard | |
| 3 | HCMUS_Beyonders | 0.74 | HCMUS_Beyonders | Sep 2026 | Official leaderboard | |
| 4 | AI_COE_Tredence | 0.74 | AI_COE_Tredence | Sep 2026 | Official leaderboard | |
| 5 | Syed Mohaiminul Hoque | 0.74 | Syed Mohaiminul Hoque | Sep 2026 | Official leaderboard | |
| 6 | Letus Pata | 0.69 | Letus Pata | Sep 2026 | Official leaderboard | |
| 7 | [Deleted] 85efbf09-6a44-42d0-a91b-f7dd9a3d8932 | 0.66 | [Deleted] 85efbf09-6a44-42d0-a91b-f7dd9a3d8932 | Oct 2026 | Official leaderboard | |
| 8 | PSGS | 0.64 | PSGS | Sep 2026 | Official leaderboard | |
| 9 | AI Duo | 0.61 | AI Duo | Oct 2026 | Official leaderboard | |
| 10 | Ethan Seefried | 0.49 | Ethan Seefried | Oct 2026 | Official leaderboard | |
| 11 | denza sikora | 0.48 | denza sikora | Sep 2026 | Official leaderboard | |
| 12 | Global_Optima | 0.48 | Global_Optima | Oct 2026 | Official leaderboard | |
| 13 | shubham sharma1111111 | 0.46 | shubham sharma1111111 | Sep 2026 | Official leaderboard | |
| 14 | amarzouyoussef | 0.45 | amarzouyoussef | Aug 2026 | Official leaderboard | |
| 15 | Truong Giang | 0.42 | Truong Giang | Sep 2026 | Official leaderboard | |
| 16 | bsenst | 0.41 | bsenst | Aug 2026 | Official leaderboard | |
| 17 | Steve K | 0.40 | Steve K | Sep 2026 | Official leaderboard | |
| 18 | sample_submission.csv | 0.25 | sample_submission.csv | Jul 2026 | Official leaderboard | |
| 19 | Himanshu Dhiman | 0.25 | Himanshu Dhiman | Jul 2026 | Official 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
All 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access Public tasks, plus a private test set.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the official leaderboard (19 entries).
- Pass Models scored 19 entries on its leaderboard, none a model we track.
- Note Newest score No scores yet.
- Note Frontier models No models scored yet.
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on kaggle.com: 19 entries at the last read, none a model we track.
- 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.