multimodal benchmark
MIABench
MIABench evaluates multimodal instruction alignment and following capabilities.
Updated Aug 7, 2026
Published models1
Registry coverage1
MetricScore
EvidenceB
MIABench leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 0.927 points | 100.0% | 1 | C |
MIABench highlights
The top published results on this benchmark's own scale.
What is MIABench?
Definition and scoring fields from the benchmark registry.
MIABench evaluates multimodal instruction alignment and following capabilities.
Scores are shown in points. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- MIABench
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- miabench|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
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 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.