CritPT
Progress Over Time
Interactive timeline showing model performance evolution on CritPT
State-of-the-art frontier
Open
Proprietary
CritPT Leaderboard
5 models
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Zhipu AI | 753B | 1.0M | $0.95 / $3.00 | ||
| 2 |  Alibaba Cloud / Qwen Team | — | 1.0M | $1.25 / $3.75 | ||
| 3 |  Thinking Machines Lab | 276B | 256K | $0.30 / $1.20 | ||
| 4 | Alibaba Cloud / Qwen Team | — | — | — | ||
| 5 | 550B | — | — |
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 5 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
GLM-5.2 from Zhipu AI currently leads the CritPT leaderboard with a score of 0.167 across 5 evaluated AI models.
FAQ
Common questions about the CritPT benchmark and leaderboard.