CritPt v2 launches: GPT-6 Astra tops at 83%, 54 points above GPT-5
ArtificialAnlys · x · 2026-10-23
CritPt v2 is live on Artificial Analysis: the authors revised all 70 research-level physics challenges, fixed underspecified statements and grader instability, and now run it agentically with code execution in an offline sandbox.
Key results:
- GPT-6 Astra (max) leads at 83%, GPT-6.1 Sol (max) 82%, Claude Opus 5.5 (max with fallback) 78%, GPT-5.6 Sol (max) 75%
- GPT-5 (high), released August 2025, scores just 29% — 54 points behind GPT-6 Astra
- The Intelligence Index updates in late October with the CritPt changes
The cost-vs-score chart shows GPT-6.1 Sol, GPT-5.6 Sol, and Gemini 4 Argon in the most attractive value quadrant.
Related event: CritPt v2 Physics Benchmark Released; GPT-6 Astra Tops at 83%(4 posts)→
More from Models
- Sophont's Holon-S1 predicts genes and biomarkers from routine pathology slides — iScienceLuvr · 2026-10-23
- Doc parsing lite mode scores 75.1 vs Azure Read's 42.3 on OmniParseBench, dominates non-Latin scripts — VikParuchuri · 2026-10-23
- Datalab open-sources Indra OCR: a 1M-parameter model that beats PaddleOCR on CPU — VikParuchuri · 2026-10-23
- The inside story behind OpenAI's million-dollar math proof — scientificamerican · 2026-10-23
- Anthropic's anti-distillation defense cuts attacks 90-99%, but expert data is still for sale — johnkorrigan · 2026-10-23
- Hugging Face CEO open to reworking evals after researcher calls its benchmarks 'extremely problematic' — ClementDelangue · 2026-10-23