Benchmark
VideoMMMU Benchmark
What is VideoMMMU?
Video-MMMU evaluates Large Multimodal Models' ability to acquire knowledge from expert-level professional videos across six disciplines through three cognitive…
- Modality
- multimodal
- Evaluates
- multimodal, reasoning, healthcare, vision
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 26
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/videommmu?top_n=500
VideoMMMU code
VideoMMMU results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Gemini 2.5 Pro Preview 06-05 | 0.836 | 2025-06-05 | evidence | |
| Gemini 3 Flash | 0.869 | 2025-12-17 | evidence | |
| Gemini 3 Pro | 0.876 | 2025-11-18 | evidence | |
| Gemini 3.1 Flash-Lite | 0.848 | 2026-03-03 | evidence | |
| GPT-4o | OpenAI | 0.612 | 2024-08-06 | evidence |
| GPT-5 | OpenAI | 0.846 | 2025-08-07 | evidence |
| GPT-5.2 | OpenAI | 0.859 | 2025-12-11 | evidence |
| Kimi K2.5 | Moonshot AI | 0.866 | 2026-01-27 | evidence |
| MiniMax M3 | MiniMax | 0.846 | 2026-06-01 | evidence |
| o3 | OpenAI | 0.833 | 2025-04-16 | evidence |
| Qwen3 VL 235B A22B Instruct | Qwen | 0.747 | 2025-09-22 | evidence |
| Qwen3 VL 235B A22B Thinking | Qwen | 0.8 | 2025-09-22 | evidence |
| Qwen3 VL 30B A3B Instruct | Qwen | 0.687 | 2025-09-22 | evidence |
| Qwen3 VL 30B A3B Thinking | Qwen | 0.75 | 2025-09-22 | evidence |
| Qwen3 VL 32B Thinking | Qwen | 0.79 | 2025-09-22 | evidence |
| Qwen3 VL 4B Instruct | Qwen | 0.562 | 2025-09-22 | evidence |
| Qwen3 VL 4B Thinking | Qwen | 0.694 | 2025-09-22 | evidence |
| Qwen3 VL 8B Instruct | Qwen | 0.653 | 2025-09-22 | evidence |
| Qwen3 VL 8B Thinking | Qwen | 0.728 | 2025-09-22 | evidence |
| Qwen3.5-122B-A10B | Qwen | 0.82 | 2026-02-24 | evidence |
| Qwen3.5-27B | Qwen | 0.823 | 2026-02-24 | evidence |
| Qwen3.5-35B-A3B | Qwen | 0.804 | 2026-02-24 | evidence |
| Qwen3.6 Plus | Qwen | 0.84 | 2026-04-02 | evidence |
| Qwen3.6-27B | Qwen | 0.844 | 2026-04-21 | evidence |
| Qwen3.6-35B-A3B | Qwen | 0.837 | 2026-04-16 | evidence |
| Qwen3.7-Plus | Qwen | 0.854 | 2026-05-31 | 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.