multimodal benchmark
PerceptionBench
PerceptionBench is Moonshot AI's internal benchmark for evaluating atomic visual perception capabilities.
Updated Aug 11, 2026
Models2
Model coverage2
MetricScore
EvidenceB
PerceptionBench Ranking
Higher score ranks better on this benchmark.
| 01 | AC | 63.5% | 100.0% | 2 | C | |
| 02 | MA | 58.5% | 0.0% | 2 | C |
PerceptionBench Score Distribution
A closer view of the leading scores on this benchmark.
PerceptionBench Highlights
The leading models and scores on this benchmark.
What is PerceptionBench?
What PerceptionBench measures and how its scores work.
PerceptionBench is Moonshot AI's internal benchmark for evaluating atomic visual perception capabilities.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- PerceptionBench
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- perceptionbench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about PerceptionBench.
Which model scores highest on PerceptionBench?
Qwen3.8 Max is currently ranked first with 63.5%.
What does PerceptionBench measure?
PerceptionBench is Moonshot AI's internal benchmark for evaluating atomic visual perception capabilities.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
2 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.