PerceptionBench (Moonshot)
Moonshot in-house benchmark of atomic visual perception skills. Scoring details unpublished.
Lab-created in-house eval (Moonshot AI). Not the same as other public benchmarks with this name.
- Level
- Everyday Most adults, without training
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Short answer A number, word or short string matched to a key.
Kimi K3.1 Pro leads with 68.3%
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
- 1 Kimi K3.1 Pro 68.3%
- 2
Qwen 3.8 Max 63.5% - 3 Kimi K3 58.5%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Kimi K3.1 Pro | 68.3% | Oct 2026 | Model card | |
| 2 | Qwen 3.8 Max | 63.5% | Aug 2026 | Model card | |
| 3 | Kimi K3 | 58.5% | Jul 2026 | Model card |
3 models have held number one since its release in Jul 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
2 labs put it in a launch post in the last six months
Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| 24 Oct 2026 | Kimi K3.1 Pro | 68.3 | PerceptionBench |
| 3 Aug 2026 | Qwen 3.8 Max | 63.5 | PerceptionBench |
| 16 Jul 2026 | Kimi K3 | 58.5 | PerceptionBench |
One system card reports it
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 27 Jul 2026 | Kimi K3 technical report | 58.5 | PerceptionBench (Table 2) | Capabilities |
More in Vision
- MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy. GPT-5.1 85.4%
- MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. Kimi K3.1 Pro 84.1%
- CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
- MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy. Qwen 3.8 Max 97.7%
- ChartQA In use Models answer human-written and generated questions about chart images that need visual and arithmetic reasoning. Scored by relaxed accuracy with a 5 percent numeric tolerance.
Command A Vision 90.9% - DocVQA In use Models answer 50,000 questions about 12,000 scanned document images by reading their text and layout. Scoring is ANLS, a string similarity to reference answers.
Seed1.5-VL 96.9%