reasoning
CritPt v2 Hard Subset
- #91high of 11611.5%
Leader: GPT-6 Astra · 72.0%
OpenAI · released 2025-08-07
Measured on 135 benchmarks.
Not ranked in this one: too little measured data for its benchmarks. Pick another ranking above.
reasoning
Leader: GPT-6 Astra · 72.0%