Artificial Analysis (@ArtificialAnlys) · 10/23/2026, 01:55:37
CritPt v2 Launches with Code-Execution Sandbox for Physics Benchmarks
Artificial Analysis launched CritPt v2, revising 70 research-level physics challenges and enabling models to solve them via an offline code-execution sandbox. The updated leaderboard shows GPT-6 Astra leading with 83%, a 54-point jump from GPT-5, highlighting rapid progress in frontier model reasoning and tool use.
SOURCE COVERAGEFull Original Report
Artificial Analysis (@ArtificialAnlys) · 2026-10-22 17
CritPt v2 has launched on Artificial Analysis: the CritPt authors have revised all 70 research-level physics challenges, and models now solve them with a code-execution tool
Following feedback from the research community, the CritPt team and physics expert collaborators reviewed every challenge, corrected underspecified statements, errors, and typos, and improved the stability of the grader. We now run CritPt v2 agentically: models can write and run code in an offline sandbox with tools for computation.
We’ll be updating the Intelligence Index in late October, including changes to CritPt.
Key takeaways:
➤ Recent OpenAI releases top the leaderboard: GPT-6 Astra (max) and GPT-6.1 Sol (max) score highest at 83% and 82%, followed by Claude Opus 5.5 (max with fallback) at 78% and GPT-5.6 Sol (max) at 75%
➤ CritPt v2 shows the rapid progress at the frontier on research-level physics: GPT-5 (high), released in August 2025, scores 29% on CritPt v2, 54 points below GPT-6 Astra (max)
Thank you to @MiniHui_zhu, @MinyangTian1, @haopeng_uiuc and the broader CritPt team for their work on this revision and their continued collaboration
