math benchmark
CritPT
CritPT is a challenging reasoning benchmark reported by Qwen for evaluating frontier mathematical and critical problem-solving capability.
Updated Aug 7, 2026
Published models4
Registry coverage4
MetricScore
EvidenceB
CritPT leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | ZA | 16.7% | 100.0% | 4 | C | |
| 2 | AC | 11.4% | 66.7% | 4 | C | |
| 3 | AC | 6.0% | 33.3% | 4 | C | |
| 4 | NV | 3.1% | 0.0% | 4 | C |
Score distribution
Top published rows on the benchmark's original scale.
CritPT highlights
The top published results on this benchmark's own scale.
What is CritPT?
Definition and scoring fields from the benchmark registry.
CritPT is a challenging reasoning benchmark reported by Qwen for evaluating frontier mathematical and critical problem-solving capability.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- CritPT
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- critpt|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about CritPT.
Which model scores highest on CritPT?
GLM-5.2 is currently ranked first with 16.7%.
What does CritPT measure?
CritPT is a challenging reasoning benchmark reported by Qwen for evaluating frontier mathematical and critical problem-solving capability.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
4 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.