Benchmark
MMBench-V1.1
Version 1.1 of MMBench, an improved bilingual benchmark for assessing multi-modal capabilities of vision-language models through multiple-choice questions…
- Modality
- multimodal
- Categories
- multimodal, reasoning, vision
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 20
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| DeepSeek VL2 | DeepSeek | 0.792 | 2024-12-13 | evidence |
| DeepSeek VL2 Small | DeepSeek | 0.793 | 2024-12-13 | evidence |
| DeepSeek VL2 Tiny | DeepSeek | 0.683 | 2024-12-13 | evidence |
| LFM2.5-VL-3B | Liquid AI | 0.81 | 2026-08-12 | evidence |
| North Micro Vision Instruct | Cohere | 0.687 | 2026-08-12 | evidence |
| Qwen2.5-Omni-7B | Qwen | 0.818 | 2025-03-27 | evidence |
| Qwen3 VL 235B A22B Instruct | Qwen | 0.899 | 2025-09-22 | evidence |
| Qwen3 VL 235B A22B Thinking | Qwen | 0.906 | 2025-09-22 | evidence |
| Qwen3 VL 30B A3B Instruct | Qwen | 0.87 | 2025-09-22 | evidence |
| Qwen3 VL 30B A3B Thinking | Qwen | 0.889 | 2025-09-22 | evidence |
| Qwen3 VL 32B Thinking | Qwen | 0.908 | 2025-09-22 | evidence |
| Qwen3 VL 4B Instruct | Qwen | 0.851 | 2025-09-22 | evidence |
| Qwen3 VL 4B Thinking | Qwen | 0.867 | 2025-09-22 | evidence |
| Qwen3 VL 8B Instruct | Qwen | 0.85 | 2025-09-22 | evidence |
| Qwen3 VL 8B Thinking | Qwen | 0.875 | 2025-09-22 | evidence |
| Qwen3.5-122B-A10B | Qwen | 0.928 | 2026-02-24 | evidence |
| Qwen3.5-27B | Qwen | 0.926 | 2026-02-24 | evidence |
| Qwen3.5-35B-A3B | Qwen | 0.915 | 2026-02-24 | evidence |
| Qwen3.6-27B | Qwen | 0.923 | 2026-04-21 | evidence |
| Qwen3.6-35B-A3B | Qwen | 0.928 | 2026-04-16 | 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.