RoughCut-Bench
Models select and order video clips or mark speech to remove from a transcript. The evaluation compares cut plans with professional editors’ annotations.
The authors compare eight models on 101 visual cases and 84 speech cases. The leaderboard reports separate metrics for each setting.
- Released
- July 2026
- Kind
- Video understanding
- Level
- University
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Subject
- Arts
- Language
- English
- Interaction
- Single turn
- Items from
- Written by experts, Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- Occupations
- Arts, design, entertainment, sports and media
- In views
- Vision
- Strongest model tested
- GPT-5.5 #21 on the capability index
- Last model added
- June 2026
- Scores refreshed
- November 20th, 2026
Gemini 3 Pro leads with 0.53 among models released by June 2026 Gemini 3 Pro leads with 0.53 among models released by June 2026
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. The project reports no combined score and ranks its first table by Visual Set-1 F1. 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. This view shows only models we track, each at its best.
The newest model with a score here came out in June 2026, 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
Gemini 3 Pro 0.53
- 2
Qwen3.7-Plus 0.52
- 3
Seed2.0 Lite (0215) 0.51
- 4
Qwen3.5-Plus 0.51
- 5 GPT-5.5 0.51
- 6 GPT-5.4 0.51
- 7 Gemini 2.5 Pro (snapshot unspecified) 0.51
- 8 GLM-5V-Turbo 0.48
Source: Official RoughCut-Bench leaderboard
- 1
Gemini 3 Pro 0.53
- 2
Qwen3.7-Plus 0.52
- 3
Seed2.0 Lite (0215) 0.51
- 4
Qwen3.5-Plus 0.51
- 5 GPT-5.5 0.51
- 6 GPT-5.4 0.51
- 7 GLM-5V-Turbo 0.48
Source: Official RoughCut-Bench leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 0.53 | Nov 2025 | Official leaderboard | |
| 2 | | 0.52 | Jun 2026 | Official leaderboard | |
| 3 | | 0.51 | Feb 2026 | Official leaderboard | |
| 4 | | 0.51 | Feb 2026 | Official leaderboard | |
| 5 | GPT-5.5 | 0.51 | Apr 2026 | Official leaderboard | |
| 6 | GPT-5.4 | 0.51 | Mar 2026 | Official leaderboard | |
| 7 | Gemini 2.5 Pro (snapshot unspecified) | 0.51 | Official leaderboard | ||
| 8 | GLM-5V-Turbo | 0.48 | Apr 2026 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 0.53 | Nov 2025 | Official leaderboard | |
| 2 | | 0.52 | Jun 2026 | Official leaderboard | |
| 3 | | 0.51 | Feb 2026 | Official leaderboard | |
| 4 | | 0.51 | Feb 2026 | Official leaderboard | |
| 5 | GPT-5.5 | 0.51 | Apr 2026 | Official leaderboard | |
| 6 | GPT-5.4 | 0.51 | Mar 2026 | Official leaderboard | |
| 7 | GLM-5V-Turbo | 0.48 | Apr 2026 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official RoughCut-Bench 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 RoughCut-Bench 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 9 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (8 entries).
- Pass Models scored 7 models we track, plus 1 other entry on its leaderboard.
- Pass Newest score The newest is from June 2026, for Qwen3.7-Plus.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.5 (#21).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on whalesong-zrs.github.io: 7 rows for models we track and 1 other entry 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.