CritPt v2 launches on Artificial Analysis: GPT-6 Astra tops the leaderboard at 83%
CritPt v2 is now live on Artificial Analysis. All 70 research-level physics problems have been fully reviewed by the authors' team, and the benchmark has been changed to agentic answering in an offline sandbox with code execution tools. GPT-6 Astra (max) and GPT-6.1 Sol (max) lead at 83% and 82% respectively, followed closely by Claude Opus 5.5 (max with fallback) at 78% and GPT-5.6 Sol (max) at 75%. GPT-5 (high), released in August 2025, scores only 29%, 54 percentage points below GPT-6 Astra (max).
Body
CritPt v2 has launched on Artificial Analysis: the CritPt authors have reviewed 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