Benchmark
VideoMME w sub. Benchmark
What is VideoMME w sub.?
The first-ever comprehensive evaluation benchmark of Multi-modal LLMs in Video analysis. Features 900 videos (254 hours) with 2,700 question-answer pairs…
- Modality
- multimodal
- Evaluates
- multimodal, video, vision
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 10
Source provenance
VideoMME w sub. results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| GPT-5 | OpenAI | 0.867 | 2025-08-07 | evidence |
| Qwen2.5 VL 32B Instruct | Qwen | 0.779 | 2025-02-28 | evidence |
| Qwen2.5 VL 7B Instruct | Qwen | 0.716 | 2025-01-26 | evidence |
| Qwen2.5-Omni-7B | Qwen | 0.724 | 2025-03-27 | evidence |
| Qwen3.5-122B-A10B | Qwen | 0.873 | 2026-02-24 | evidence |
| Qwen3.5-27B | Qwen | 0.87 | 2026-02-24 | evidence |
| Qwen3.5-35B-A3B | Qwen | 0.866 | 2026-02-24 | evidence |
| Qwen3.6-27B | Qwen | 0.877 | 2026-04-21 | evidence |
| Qwen3.6-35B-A3B | Qwen | 0.866 | 2026-04-16 | evidence |
| Qwen3.8 Max | Qwen | 0.904 | 2026-08-02 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.