Benchmark
CritPt
Research-level physics reasoning; small expert-authored set.
- Released
- 2025-09-30
- Categories
- science
- Openness
- unknown
- Source
- model_reports
- Reported scores
- 3
Reported scores
model_reports
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| GLM-5.2 | Z.ai | 20.9 | 2026-06-16 | evidence |
| Hy4 preview | Tencent | 16.9 | 2026-08-28 | evidence |
| Kimi K3 | Moonshot AI | 23.4 | 2026-06-13 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.