math benchmark
CritPT Leaderboard
CritPT is a challenging reasoning benchmark reported by Qwen for evaluating frontier mathematical and critical problem-solving capability.
Updated Aug 17, 2026
Models5
Model coverage5
MetricScore
EvidenceB
CritPT Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelZA | Score16.7% | Percentile100.0% | Participants5 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score11.4% | Percentile75.0% | Participants5 | EvidenceC | Evaluated |
| Rank03 | ModelTM | Score8.3% | Percentile50.0% | Participants5 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score6.0% | Percentile25.0% | Participants5 | EvidenceC | Evaluated |
| Rank05 | ModelNV | Score3.1% | Percentile0.0% | Participants5 | EvidenceC | Evaluated |
CritPT Highlights
The leading models and scores on this benchmark.
CritPT Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for CritPT
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis critpt AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01ZAGLM-5.2Zhipu AI
- Score
- 16.7%
- Price
- $1.4 input / $4.4 output per 1M tokens
Strengths
- Ranks #1 of 5 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures CritPT, not total model capability
- 02ACQwen3.7 MaxAlibaba Cloud / Qwen Team
- Score
- 11.4%
- Price
- $2.5 input / $7.5 output per 1M tokens
- Speed
- Up to 5.8 tok/s via Together
Strengths
- Ranks #2 of 5 compared models
- 75th percentile on this benchmark
- C evidence result
Considerations
- This result measures CritPT, not total model capability
- 03TMInkling-SmallThinking Machines Lab
- Score
- 8.3%
Strengths
- Ranks #3 of 5 compared models
- 50th percentile on this benchmark
- C evidence result
Considerations
- This result measures CritPT, not total model capability
- 04ACQwen3.7-PlusAlibaba Cloud / Qwen Team
- Score
- 6.0%
- Price
- $0.50 input / $3.0 output per 1M tokens
Strengths
- Ranks #4 of 5 compared models
- 25th percentile on this benchmark
- C evidence result
Considerations
- This result measures CritPT, not total model capability
- 05NV
- Score
- 3.1%
- Price
- $0.50 input / $2.5 output per 1M tokens
Strengths
- Ranks #5 of 5 compared models
- 0th percentile on this benchmark
- C evidence result
Considerations
- This result measures CritPT, not total model capability
Selection summary
Best AI Models for CritPT
GLM-5.2 currently leads CritPT with 16.7%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is CritPT?
What CritPT measures and how its scores work.
CritPT is a challenging reasoning benchmark reported by Qwen for evaluating frontier mathematical and critical problem-solving capability.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- CritPT
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- critpt|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
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?
5 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.