Assembly101-O
Models watch people assemble toy vehicles and flag the first procedural mistake. Training uses correct procedures, and evaluation stops at the first mistake in an incorrect sequence.
PREGO combined video recognition with GPT-3.5 or Llama. A later task graph study scored its own predictions on Assembly101-O.
- Made by
- Sapienza University of Rome and University of Catania
- Released
- April 2024
- Kind
- Video understanding
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Prediction
- Tasks
- All public
- Measures
- Capability
- Interaction
- Single turn
- Items from
- Another benchmark
- Refresh
- One fixed set
- Run by
- Anyone
- Based on
- A version of another benchmark
- In views
- Vision
LLAMA tops the leaderboard with 41.8%
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.
- 1 LLAMA 41.8%
- 2 GPT-3.5 (snapshot unspecified) 27.3%
- 3 OadTR 20.7%
Source: The Assembly101-O paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | LLAMA | 41.8% | PREGO with MiniRoad | Official leaderboard | |
| 2 | GPT-3.5 (snapshot unspecified) | 27.3% | PREGO with MiniRoad | Official leaderboard | |
| 3 | OadTR | 20.7% | OadTR for MD | 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 7 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 pass 4 notes
- Pass Independent runs Scores from the benchmark’s paper (3 entries).
- Note Models scored 3 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: 3 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.