Benchmark
MIABench
What is MIABench?
MIABench evaluates multimodal instruction alignment and following capabilities. Benchmark Radar tracks 1 reported scores for MIABench, cited by 1 source…
- Modality
- multimodal
- Evaluates
- multimodal, instruction following, vision
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 1
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/miabench?top_n=500
MIABench results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Qwen3 VL 235B A22B Thinking | Qwen | 0.927 | 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.