All benchmarks

PerceptionBench

Progress Over Time

Interactive timeline showing model performance evolution on PerceptionBench

State-of-the-art frontier
Open
Proprietary

PerceptionBench Leaderboard

1 models
ContextCostLicense
1
Moonshot AI
Kimi K3New
Moonshot AI
2.8T1.0M$3.00 / $15.00
Notice missing or incorrect data?
About this benchmark

What is PerceptionBench?

PerceptionBench is Moonshot AI's internal benchmark for evaluating atomic visual perception capabilities.

PerceptionBench is a multimodal benchmark evaluating models on multimodal, reasoning, and vision tasks. LLM Stats tracks 1 models on this benchmark, scored on a 0–1 scale. The current average is 0.6, with the leader at 0.6.

Compare leaders on the best AI for multimodal, best AI for reasoning and best AI for vision leaderboards.

Current leaders

Kimi K3 from Moonshot AI currently leads the PerceptionBench leaderboard with a score of 0.585 across 1 evaluated AI models.

1Kimi K3Moonshot AI58.5%

FAQ

Common questions about the PerceptionBench benchmark and leaderboard.

What is the PerceptionBench benchmark?

PerceptionBench is Moonshot AI's internal benchmark for evaluating atomic visual perception capabilities.

What is the PerceptionBench leaderboard?

The PerceptionBench leaderboard ranks 1 AI models based on their performance on this benchmark. Currently, Kimi K3 by Moonshot AI leads with a score of 0.585. The average score across all models is 0.585.

What is the highest PerceptionBench score?

The highest PerceptionBench score is 0.585, achieved by Kimi K3 from Moonshot AI.

How many models are evaluated on PerceptionBench?

1 models have been evaluated on the PerceptionBench benchmark, with 0 verified results and 1 self-reported results.

What categories does PerceptionBench cover?

PerceptionBench is categorized under multimodal, reasoning, and vision. The benchmark evaluates multimodal models.

What is the best open-source model on PerceptionBench?

Kimi K3 by Moonshot AI is the top-ranked open-source model on PerceptionBench, with a score of 0.585 (rank #1).

Which model offers the best value on PerceptionBench?

Among models scoring within 10% of the leader, Kimi K3 from Moonshot AI is the cheapest, at $3.00 per million input tokens with a score of 0.585.

How recent are the PerceptionBench leaderboard results?

The PerceptionBench leaderboard was last updated in July 2026 and currently includes 1 evaluated models.