multimodal benchmark
VideoMME w sub. Leaderboard
The first-ever comprehensive evaluation benchmark of Multi-modal LLMs in Video analysis. Features 900 videos (254 hours) with 2,700 question-answer pairs covering 6 primary visual domains and 30 subfields. Evaluates temporal understanding across short (11 seconds) to long (1 hour) videos with multi-modal inputs including video frames, subtitles, and audio.
Updated Aug 17, 2026
Models10
Model coverage10
MetricScore
EvidenceB
VideoMME w sub. Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAC | Score90.4% | Percentile100.0% | Participants10 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score87.7% | Percentile88.9% | Participants10 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score87.3% | Percentile77.8% | Participants10 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score87.0% | Percentile66.7% | Participants10 | EvidenceC | Evaluated |
| Rank05 | ModelOP | Score86.7% | Percentile55.6% | Participants10 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score86.6% | Percentile44.4% | Participants10 | EvidenceC | Evaluated |
| Rank07 | ModelAC | Score86.6% | Percentile33.3% | Participants10 | EvidenceC | Evaluated |
| Rank08 | ModelAC | Score77.9% | Percentile22.2% | Participants10 | EvidenceC | Evaluated |
| Rank09 | ModelAC | Score72.4% | Percentile11.1% | Participants10 | EvidenceC | Evaluated |
| Rank10 | ModelAC | Score71.6% | Percentile0.0% | Participants10 | EvidenceC | Evaluated |
VideoMME w sub. Highlights
The leading models and scores on this benchmark.
VideoMME w sub. Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for VideoMME w sub.
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis videomme w sub. AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01ACQwen3.8 MaxAlibaba Cloud / Qwen Team
- Score
- 90.4%
- Price
- $2.0 input / $6.0 output per 1M tokens
Strengths
- Ranks #1 of 10 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures VideoMME w sub., not total model capability
- 02ACQwen3.6-27BAlibaba Cloud / Qwen Team
- Score
- 87.7%
- Price
- $0.60 input / $3.6 output per 1M tokens
- Speed
- Up to 6.1 tok/s via Novita
Strengths
- Ranks #2 of 10 compared models
- 89th percentile on this benchmark
- C evidence result
Considerations
- This result measures VideoMME w sub., not total model capability
- 03ACQwen3.5-122B-A10BAlibaba Cloud / Qwen Team
- Score
- 87.3%
- Price
- $0.40 input / $3.2 output per 1M tokens
Strengths
- Ranks #3 of 10 compared models
- 78th percentile on this benchmark
- C evidence result
Considerations
- This result measures VideoMME w sub., not total model capability
- 04ACQwen3.5-27BAlibaba Cloud / Qwen Team
- Score
- 87.0%
- Price
- $0.30 input / $2.4 output per 1M tokens
- Speed
- Up to 6.7 tok/s via Novita
Strengths
- Ranks #4 of 10 compared models
- 67th percentile on this benchmark
- C evidence result
Considerations
- This result measures VideoMME w sub., not total model capability
- 05OPGPT-5OpenAI
- Score
- 86.7%
- Price
- $1.3 input / $10 output per 1M tokens
- Speed
- Up to 100 tok/s via OpenAI
Strengths
- Ranks #5 of 10 compared models
- 56th percentile on this benchmark
- C evidence result
Considerations
- This result measures VideoMME w sub., not total model capability
Selection summary
Best AI Models for VideoMME w sub.
Qwen3.8 Max currently leads VideoMME w sub. with 90.4%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is VideoMME w sub.?
What VideoMME w sub. measures and how its scores work.
The first-ever comprehensive evaluation benchmark of Multi-modal LLMs in Video analysis. Features 900 videos (254 hours) with 2,700 question-answer pairs covering 6 primary visual domains and 30 subfields. Evaluates temporal understanding across short (11 seconds) to long (1 hour) videos with multi-modal inputs including video frames, subtitles, and audio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- VideoMME w sub.
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- videomme-w-sub.|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about VideoMME w sub..
Which model scores highest on VideoMME w sub.?
Qwen3.8 Max is currently ranked first with 90.4%.
What does VideoMME w sub. measure?
The first-ever comprehensive evaluation benchmark of Multi-modal LLMs in Video analysis. Features 900 videos (254 hours) with 2,700 question-answer pairs covering 6 primary visual domains and 30 subfields. Evaluates temporal understanding across short (11 seconds) to long (1 hour) videos with multi-modal inputs including video frames, subtitles, and audio.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
10 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.