GPT-5.6 Sol hits 32% on CritPt physics benchmark, up from 4% a year ago
geoffwolfe · x · 2026-08-17
The CritPt benchmark tests models on unpublished research problems from 60+ physicists. A year ago, the best model solved only 4%. Today, GPT-5.6 Sol leads at 32%, with Fable 5 at 29%. This marks the fastest capability jump observed, though 2/3 of physics research remains out of reach.
More from Research
- ImageNet should retire: DiT method rankings negatively correlate between ImageNet and text-to-image — YouJiacheng · 2026-10-16
- GAE paper learns a geometry-native latent space for 3D-consistent world generation — yshan2u · 2026-10-16
- Agents turn conservative as context grows: edits shrink from 150 to 30 lines — dbreunig · 2026-10-16
- LMR-BENCH at EMNLP 2025 tests whether LLM agents can reproduce real LLM research — ZhiyuChen4 · 2026-10-16
- Ex-OpenAI researcher claims most neurons are legible now; critics call it hype — anshulkundaje · 2026-10-16
- Physicist pushes back on ML community's acceptance that models may be beyond understanding — tszzl · 2026-10-16