COIN instructional video analysis
Models recognize steps in videos of people completing everyday tasks. The benchmark supplies annotated actions and their time intervals.
- Made by
- COIN team
- Released
- March 2019
- Kind
- Video understanding
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Prediction
- Tasks
- All public
- Measures
- Capability
- Language
- English
- In and out
- Video → Text, Time series
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Vision
SSN+TC-RGB tops the leaderboard with 9.33%
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The headline is mean average precision for step localization at IoU 0.5. 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 SSN+TC-RGB 9.33%
- 2 SSN+TC-Fusion 9.05%
- 3 SSN-Fusion 8.12%
- 4 SSN-RGB 7.79%
- 5 SSN+TC-Flow 5.52%
- 6 SSN-Flow 4.94%
- 7 R-C3D+TC 3.08%
- 8 R-C3D 2.82%
Source: The COIN instructional video analysis paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | SSN+TC-RGB | 9.33% | Official leaderboard | ||
| 2 | SSN+TC-Fusion | 9.05% | Official leaderboard | ||
| 3 | SSN-Fusion | 8.12% | Official leaderboard | ||
| 4 | SSN-RGB | 7.79% | Official leaderboard | ||
| 5 | SSN+TC-Flow | 5.52% | Official leaderboard | ||
| 6 | SSN-Flow | 4.94% | Official leaderboard | ||
| 7 | R-C3D+TC | 3.08% | Official leaderboard | ||
| 8 | R-C3D | 2.82% | 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 Audio and video
- Video-MMMU In use 300 expert-level lecture videos with questions testing perception, comprehension and adaptation of knowledge. Accuracy.
Qwen 3.8 Max 88.7%
- LVBench In use Hours-long video understanding with multiple-choice questions on reasoning, grounding and summarization.
Gemini 4 Argon 91.7%
- MMVU In use 3,000 expert-annotated questions on videos across 27 disciplines. Multiple-choice and open-ended accuracy.
Qwen 3.8 Max 82.4%
- MLVU In use Multi-task long video understanding (minutes to hours) with multiple-choice and generation tasks. Accuracy.
Qwen 3.8 Max 90.8%
- FLEURS In use Models transcribe read speech in 102 languages built from FLoRes-101 sentences. Model cards usually report word error rate, so lower scores are better.
Phi-4-multimodal 4.00%
- VoiceBench In use Spoken instructions with speaker, environment and content variation. Voice assistant responses scored by GPT judge or rules.
Qwen3.5-Omni-Plus 93.1%
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 (8 entries).
- Pass Models scored 8 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 coin-dataset.github.io: 8 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.