Benchmark
MLVU-M Benchmark
What is MLVU-M?
MLVU-M benchmark. Benchmark Radar tracks 8 reported scores for MLVU-M, cited by 1 source documents.
- Modality
- text
- Evaluates
- general
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 8
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/mlvu-m?top_n=500
MLVU-M results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Qwen2.5 VL 72B Instruct | Qwen | 0.746 | 2025-01-26 | evidence |
| Qwen3 VL 30B A3B Instruct | Qwen | 0.813 | 2025-09-22 | evidence |
| Qwen3 VL 30B A3B Thinking | Qwen | 0.789 | 2025-09-22 | evidence |
| Qwen3 VL 32B Instruct | Qwen | 0.821 | 2025-09-22 | evidence |
| Qwen3 VL 4B Instruct | Qwen | 0.753 | 2025-09-22 | evidence |
| Qwen3 VL 4B Thinking | Qwen | 0.757 | 2025-09-22 | evidence |
| Qwen3 VL 8B Instruct | Qwen | 0.781 | 2025-09-22 | evidence |
| Qwen3 VL 8B Thinking | Qwen | 0.751 | 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.