Multimodal & Grounded benchmark
PerceptionBench leaderboard
PerceptionBench (Internal). Every model the catalog carries a published PerceptionBench value for, ranked by that value.
CategoryMultimodal & Grounded
MeasureInternal evaluation score
TasksInternal atomic visual-perception tasks
DifficultyFine-grained visual perception
Published byKimi K3: Open Frontier Intelligence
Moonshot AI's internal benchmark for atomic visual perception capabilities.
PerceptionBench ranking
3 models with a published PerceptionBench value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Internal evaluation score |
|---|---|---|---|
| 1 |  Qwen3.8 Max | Alibaba | 63.5 |
| 2 |  Kimi K3 | Moonshot AI | 58.5 |
| 3 | DSdots3-note Preview | Dots Studio | 53.4 |
Evidence key: Observed
Rows are ordered by the value Kimi K3: Open Frontier Intelligence published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.