Benchmark
MMMU (val)
Validation set of the Massive Multi-discipline Multimodal Understanding and Reasoning benchmark. Features college-level multimodal questions across 6 core…
- Modality
- multimodal
- Categories
- multimodal, reasoning, general, healthcare, vision
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 13
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Gemma 3 12B | 0.596 | 2025-03-12 | evidence | |
| Gemma 3 27B | 0.649 | 2025-03-12 | evidence | |
| Gemma 3 4B | 0.488 | 2025-03-12 | evidence | |
| LFM2.5-VL-3B | Liquid AI | 0.484 | 2026-08-12 | evidence |
| North Micro Vision Instruct | Cohere | 0.329 | 2026-08-12 | evidence |
| Qwen3 VL 30B A3B Instruct | Qwen | 0.742 | 2025-09-22 | evidence |
| Qwen3 VL 30B A3B Thinking | Qwen | 0.76 | 2025-09-22 | evidence |
| Qwen3 VL 32B Instruct | Qwen | 0.76 | 2025-09-22 | evidence |
| Qwen3 VL 32B Thinking | Qwen | 0.781 | 2025-09-22 | evidence |
| Qwen3 VL 4B Instruct | Qwen | 0.674 | 2025-09-22 | evidence |
| Qwen3 VL 4B Thinking | Qwen | 0.708 | 2025-09-22 | evidence |
| Qwen3 VL 8B Instruct | Qwen | 0.696 | 2025-09-22 | evidence |
| Qwen3 VL 8B Thinking | Qwen | 0.741 | 2025-09-22 | 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.