Benchmark
PerceptionBench
Scores are percentages.
All reasoning benchmarksScores from LLM Stats data.
- Models measured
- 4
- Scores recorded
- 4
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 61.9%
- Mean
- 63.5%
- Median
- 4.3%
- Std dev
- 57.5%
- 10th percentile
- 68.3%
- 90th percentile
- 57.5%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Kimi K3.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 68.3% |
| 2 | Qwen3.8 Max· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 63.5% |
| 3 | Kimi K3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 58.5% |
| 4 | Inkling 2 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 57.5% |
Data credits: Data by LLM Stats