PhysCodeBench: leaderboard
PhysCodeBench (2026) tests whether language models write Genesis physics simulation code for natural-language descriptions of scenes with rigid bodies, soft bodies, fluids and mechanisms. Total score from 0 to 100 for execution, output files, video alignment with the instruction and motion smoothness; higher is better.
Metric: PhysCodeEval total score (0-100): code quality (50 points for executing and writing the expected simulation file) plus simulation fidelity (50 points for CLIPScore alignment of the rendered video with the instruction and flow-based motion smoothness) of Genesis physics-simulation programs generated zero-shot from natural-language scene descriptions on the 200-example PhysCodeBench test set (mean of five attempts, temperature 0.1, 4,096-token cap), with the engine documentation in context (the full 100K-token corpus for long-context models, 20K tokens of BM25-retrieved sections for 32K-context models); higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 7 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude 3.5 Sonnet | 35.9 | #752 |
| 2 | GPT-4o | 33.8 | #751 |
| 3 | Gemini 2.0 Pro | 31.6 | #671 |
| 4 | DeepSeek R1 | 29.5 | #482 |
| 5 | DeepSeek R1 Distill Qwen 32B | 27.6 | #1834 |
| 6 | QwQ-32B | 15.5 | #907 |
| 7 | PhysCodeBench Qwen-2.5-32B (checkpoint unspecified) | 1.9 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=physcodebench · How It Works · Data refreshed daily, snapshot 2026-11-21.