instruction following benchmark
MIABench
MIABench evaluates multimodal instruction alignment and following capabilities.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
MIABench Ranking
Higher score ranks better on this benchmark.
| 01 | AC | 0.927 points | 100.0% | 1 | C |
MIABench Highlights
The leading models and scores on this benchmark.
What is MIABench?
What MIABench measures and how its scores work.
MIABench evaluates multimodal instruction alignment and following capabilities.
Scores are shown in points. This benchmark is not independently verified and has an evidence level of B.
- Family
- MIABench
- Modality
- multimodal
- Primary category
- instruction following
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- miabench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about MIABench.
Which model scores highest on MIABench?
Qwen3 VL 235B A22B Thinking is currently ranked first with 0.927 points.
What does MIABench measure?
MIABench evaluates multimodal instruction alignment and following capabilities.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.