SciVid
Video models answer questions about scientific videos across several disciplines. The benchmark tests whether models recognize procedures, objects, and events in specialized footage.
The Google DeepMind repository releases evaluation data and scripts for a cross-domain video benchmark.
- Made by
- Google DeepMind
- Released
- July 2025
- Level
- University
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Subject
- Biological sciences, Physical sciences
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Vision, Biology and medicine
DinoV2-L tops the leaderboard with 86.7%
Best score per entry from the benchmark's paper, read on November 21st, 2026. A paper’s table doesn’t add newer models. The paper reports no overall score, so this is the CalMS21 mAP column, which it lists first. 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.
- 1 DinoV2-L 86.7%
- 2 DinoV2-g 86.6%
- 3 VideoMAEv2-g 86.2%
- 4 VideoPrism-g 85.5%
- 5 VideoPrism-B 83.2%
- 6 V-JEPA-L 82.9%
- 7 V-JEPA-H 82.8%
- 8 4DS-e 81.7%
- 9 VideoMAE-H 78.2%
- 10 VideoMAE-L 77.9%
- 11 4DS-L 77.8%
- 12 VideoMAE-B 66.5%
Source: The SciVid paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | DinoV2-L | 86.7% | Official leaderboard | ||
| 2 | DinoV2-g | 86.6% | Official leaderboard | ||
| 3 | VideoMAEv2-g | 86.2% | Official leaderboard | ||
| 4 | VideoPrism-g | 85.5% | Official leaderboard | ||
| 5 | VideoPrism-B | 83.2% | Official leaderboard | ||
| 6 | V-JEPA-L | 82.9% | Official leaderboard | ||
| 7 | V-JEPA-H | 82.8% | Official leaderboard | ||
| 8 | 4DS-e | 81.7% | Official leaderboard | ||
| 9 | VideoMAE-H | 78.2% | Official leaderboard | ||
| 10 | VideoMAE-L | 77.9% | Official leaderboard | ||
| 11 | 4DS-L | 77.8% | Official leaderboard | ||
| 12 | VideoMAE-B | 66.5% | 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 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
All 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the benchmark’s paper (12 entries).
- Pass Models scored 12 entries on its leaderboard, none a model we track.
- Note Newest score No scores yet.
- Note Frontier models No models scored yet.
- Note Headroom No scores yet.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 12 entries at the last read, none a model we track.
- Pass Last read November 21st, 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.