CritPT
Progress Over Time
Interactive timeline showing model performance evolution on CritPT
State-of-the-art frontier
Open
Proprietary
CritPT Leaderboard
6 models
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Tencent | 770B | — | — | ||
| 2 |  Zhipu AI | 753B | 1.0M | $0.75 / $2.40 | ||
| 3 |  Alibaba Cloud / Qwen Team | — | 1.0M | $1.25 / $3.75 | ||
| 4 |  Thinking Machines Lab | 276B | 524K | $0.30 / $1.20 | ||
| 5 | Alibaba Cloud / Qwen Team | — | — | — | ||
| 6 | 550B | 262K | $0.50 / $2.20 |
Notice missing or incorrect data?
What is CritPT?
CritPT is a challenging reasoning benchmark reported by Qwen for evaluating frontier mathematical and critical problem-solving capability.
CritPT is a text benchmark evaluating models on math and reasoning tasks. LLM Stats tracks 6 models on this benchmark, scored on a 0–1 scale. The current average is 0.1, with the leader at 0.2.
Compare leaders on the best AI for math and best AI for reasoning leaderboards.
Current leaders
Hy4 preview from Tencent currently leads the CritPT leaderboard with a score of 0.169 across 6 evaluated AI models.
FAQ
Common questions about the CritPT benchmark and leaderboard.