VideoScore-Bench v2
Version 2
Models score 500 generated videos on visual quality, agreement with the prompt, and physical consistency. The evaluation checks their ratings against human scores.
The EVA-RSI team ran this test separately from the original VideoScore-Bench. The public test file contains human ratings for all three dimensions.
- Made by
- TIGER Lab and collaborators
- Released
- September 2025
- Kind
- Video understanding
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Generated, Written by crowdworkers
- Refresh
- New versions replace it
- Run by
- Anyone
- Based on
- VideoScore-Bench
- In views
- Vision
- Strongest model tested
- GPT-5 #71 on the capability index
- Last model added
- August 2025
- Scores refreshed
- November 20th, 2026
VideoScore2 tops the leaderboard with 44.4% Claude Sonnet 4 leads with 28.9% among models released by August 2025
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. The best model we track is Claude Sonnet 4, at 28.9%. This view shows only models we track, each at its best.
The newest model with a score here came out in August 2025, 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
- 44.4 VideoScore2
- 38.4 VideoScore1.1
- 36.6 VisionReward
- 34.0 Dover
- 32.5 DeQA-Score
- 31.7 Q-Insight
- 28.9 Claude Sonnet 4
- 28.7 GLM-4.1V-9B-Thinking
- 28.2 Q-Align
- 28.1 ImageReward
- 27.9 Gemini-2.5-Pro (snapshot unspecified)
- 26.2 GPT-5
- 26.2 VideoReward
- 25.1 UnifiedReward
- 22.4 VideoPhy2-AutoEval
- 15.6 AIGVE-MACS
- 1 VideoScore2 44.4%
- 2 VideoScore1.1 38.4%
- 3 VisionReward 36.6%
- 4 Dover 34%
- 5 DeQA-Score 32.5%
- 6 Q-Insight 31.7%
- 7 Claude Sonnet 4 28.9%
- 8 GLM-4.1V-9B-Thinking 28.7%
- 9 Q-Align 28.2%
- 10 ImageReward 28.1%
- 11 Gemini-2.5-Pro (snapshot unspecified) 27.9%
- 12 GPT-5 26.2%
- 13 VideoReward 26.2%
- 14 UnifiedReward 25.1%
- 15 VideoPhy2-AutoEval 22.4%
- 16 AIGVE-MACS 15.6%
Source: The VideoScore-Bench v2 paper
- 1 Claude Sonnet 4 28.9%
- 2 GLM-4.1V-9B-Thinking 28.7%
- 3 GPT-5 26.2%
Source: The VideoScore-Bench v2 paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | VideoScore2 | 44.4% | Official leaderboard | ||
| 2 | VideoScore1.1 | 38.4% | Official leaderboard | ||
| 3 | VisionReward | 36.6% | Official leaderboard | ||
| 4 | Dover | 34% | Official leaderboard | ||
| 5 | DeQA-Score | 32.5% | Official leaderboard | ||
| 6 | Q-Insight | 31.7% | Official leaderboard | ||
| 7 | Claude Sonnet 4 | 28.9% | May 2025 | Official leaderboard | |
| 8 | GLM-4.1V-9B-Thinking | 28.7% | Jul 2025 | Official leaderboard | |
| 9 | Q-Align | 28.2% | Official leaderboard | ||
| 10 | ImageReward | 28.1% | Official leaderboard | ||
| 11 | Gemini-2.5-Pro (snapshot unspecified) | 27.9% | Official leaderboard | ||
| 12 | GPT-5 | 26.2% | Aug 2025 | Official leaderboard | |
| 13 | VideoReward | 26.2% | Official leaderboard | ||
| 14 | UnifiedReward | 25.1% | Official leaderboard | ||
| 15 | VideoPhy2-AutoEval | 22.4% | Official leaderboard | ||
| 16 | AIGVE-MACS | 15.6% | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Sonnet 4 | 28.9% | May 2025 | Official leaderboard | |
| 2 | GLM-4.1V-9B-Thinking | 28.7% | Jul 2025 | Official leaderboard | |
| 3 | GPT-5 | 26.2% | Aug 2025 | Official leaderboard |
Rankings by part
We read 3 parts from the benchmark’s paper: Visual Quality, Text Alignment and Physical/Common-sense Consistency. Each ranks models on one part of the test. GLM-4.1V-9B-Thinking leads 2 of them, and Claude Sonnet 4 leads the other one. Arrows show how far a model moved from its overall rank among the models we track.
Visual Quality
3 models we track have a score here.
- 1 GLM-4.1V-9B-Thinking ↑1 33.3%
- 2 Claude Sonnet 4 ↓1 33.1%
- 3 GPT-5 30.7%
Text Alignment
3 models we track have a score here.
- 1 GLM-4.1V-9B-Thinking ↑1 31.5%
- 2 Claude Sonnet 4 ↓1 29.9%
- 3 GPT-5 27.9%
Physical/Common-sense Consistency
3 models we track have a score here.
- 1 Claude Sonnet 4 23.9%
- 2 GLM-4.1V-9B-Thinking 21.4%
- 3 GPT-5 20.1%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The VideoScore-Bench v2 paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official VideoScore-Bench v2 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.
Versions
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
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 15 months ago, in August 2025, for GPT-5. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
- Pass Independent runs Scores from the benchmark’s paper (16 entries).
- Pass Models scored 3 models we track, plus 13 other entries on its leaderboard.
- Warning Newest score The newest came 15 months ago, in August 2025, for GPT-5.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5 (#71).
- Pass Headroom The best is 28.9%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 3 rows for models we track and 13 other entries 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.