P1-235B-A22B

<div align="center"> <h1 style="font-size: 2em; font-weight: bold;">P1: Mastering Physics Olympiads with Reinforcement Learning</h1> </div> <p align="center"> <a href="https://prime-rl.github.io/P1/"><b>🌐 P1 Project Page</b></a> | <a href="https://phyarena.github.io/"><b>🏆 HiPhO Leaderboard</b></a> </p> <p align="center"> <img src="https://raw.githubusercontent.com/PRIME-RL/P1/main/docs/imgs/Score_IPhO_2025_P1_v2.jpg" style="width: 800px" align=center> </p> <p align="center"> <i>Achieving gold medal at the International Physics Olympiad (IPhO 2025)</i> </p>

Model Description

P1-235B-A22B is the flagship model of the P1 series, a state-of-the-art open-source large language model specialized in physics reasoning. Built on Qwen3-235B-A22B-Thinking-2507 and tuned through multi-stage reinforcement learning on curated physics competition data, P1-235B-A22B marks a historic achievement as the first open-source model to win gold at the International Physics Olympiad (IPhO 2025).

Key Highlights

• 🏆 IPhO 2025 Gold Medal: First open-source model to achieve gold medal status (21.2/30 points)
• 🥇 HiPhO Benchmark Leader: 12 gold medals and 1 silver medal across 13 top international physics contests
• 🥇 Overall Champion: When paired with PhysicsMinions multi-agent system, achieves #1 ranking with 38.4 points, surpassing Gemini-2.5-Pro (37.7) and GPT-5 (37.4)

Performance Benchmarks

IPhO 2025 Results

<div align="center"> </div>

HiPhO Comprehensive Results

<div align="center"> </div>

Generalization to STEM Tasks

P1-235B-A22B demonstrates excellent general capabilities across various benchmarks. As shown below, P1-235B-A22B achieves better performance than its base model Qwen3-235B-A22B-Thinking-2507 on multiple tasks, further validating the strong generalization of P1 series models.

<div align="center"> </div>

Usage

Basic Inference

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load model and tokenizer
model_name = "P1-235B-A22B"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)

# Physics problem solving
prompt = """Solve this physics problem:

A block of mass m = 2.0 kg slides down a rough incline at angle θ = 30° 
with coefficient of friction μ = 0.2. Calculate the acceleration of the block.

Provide a detailed solution with reasoning steps."""

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
    **inputs,
    max_length=81920,
    temperature=0.6,
    top_p=0.9,
    do_sample=True
)

solution = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(solution)

🙏 Acknowledgements

We are grateful to the open-source community for their invaluable contributions. Special thanks to:

• Qwen3 - for providing the foundational base models that powered our research
• slime - for their innovative work on efficient reinforcement learning framework that powered our training pipeline
• verl - for the versatile reinforcement learning framework that enabled our training pipeline
• sglang - for the efficient LLM serving and inference infrastructure
• Megatron-LM - for the large-scale model training framework

Citation

@misc{p1-2025,
    title={P1: Mastering Physics Olympiads with Reinforcement Learning},
    author={P1 Team},
    year={2025},
    url={https://prime-rl.github.io/P1/}
}

</div>