BENCHMARK EVIDENCE / UNDER-REVIEW
CritPt
frontier science reasoning. Metric: score. Direction: higher-is-better. Results below stay separated by evaluator evidence type and comparable group.
3observations
Artificial Analysisevaluator
under-reviewstatus
2026-10-04verified
METHOD
Read the score with its configuration.
Scores from different comparable groups are intentionally not merged into one ranking. Reasoning effort, tools, fallback behavior, evaluator and benchmark version stay attached to every observation.
- Artificial Analysis currently labels CritPt under review.
- SXF displays the observation with a warning and never uses CritPt alone for a quality conclusion.
independent
3 observationsartificial-analysis-v4.3.2
| Model | Score | Reasoning | Tools | Source |
|---|---|---|---|---|
| Claude Opus 5.5 | 32.0% | max | benchmark-defined | Evidence ↗ |
| GPT-6 Astra | 29.0% | high | benchmark-defined | Evidence ↗ |
| GPT-6 Sol | 25.0% | high | benchmark-defined | Evidence ↗ |