𝗣𝗵𝘆𝘀𝗶𝗰𝘀 is one of the sharpest testbeds when reasoning models move...

@stingning
Ning Ding@stingning
22 views Oct 25, 2025 ~1 min read
Advertisement
1
𝗣𝗵𝘆𝘀𝗶𝗰𝘀 is one of the sharpest testbeds when reasoning models move from puzzle-solving to realistic scientific reasoning.

We have trained 𝗣𝟭 – a serie of models that achieved 𝗴𝗼𝗹𝗱 𝗺𝗲𝗱𝗮𝗹-𝗹𝗲𝘃𝗲𝗹 𝗽𝗲𝗿𝗳𝗼𝗿𝗺𝗮𝗻𝗰𝗲 in the Physics Olympiad.🥇
Media image
2
The flagship model P1-235B-A22B wins 12 golds and 1 silver across 13 top international/regional physics contests, tying Gemini-2.5-Pro for first on the medal table, and becomes the first open-source model to win gold at IPhO 2025.
Media image
3
The proposed co-evolution multi-agent system, PhysicsMinions, further boosts P1 to No.1 on both IPhO 2025 and HiPhO overall scores, outperforming Gemini-2.5-Pro and GPT-5.
Media image
4
HiPhO compiles 13 olympiad-level contests from 2024–2025 including IPhO, APhO, and EuPhO. Using official rubrics, it scores answers and processes with fine-grained, human-aligned criteria.

arxiv.org/abs/2509.07894
5
With this multi-stage RL strategy, P1 achieves sustained, long-term improvements over the base language model.
Media image
6
Beyond physics reasoning, P1 improves across multiple domains, including math, coding, and STEM benchmarks, demonstrating strong generalization of physics reasoning.
Media image
7
Case study.
Media image
8
We thank @Alibaba_Qwen @Zai_org (slime) @lmsysorg @verl_project @sgl_project for their strong base and infrastructure!
9
Repo: github.com/PRIME-RL/P1
Blog (bilingual): prime-rl.github.io/P1/

Full report coming soon!
Actions
What You Can Do
  • Export as PDF or Markdown
  • Batch Export to Notion
  • Bookmark & Highlight
  • Screenshot Tweet
Create Free Account

Includes 7-day Premium trial

Advertisement