CausalPhys - Anticipation: leaderboard
CausalPhys (2026) tests vision-language models on physical reasoning questions over real-world images and videos, each paired with an expert causal graph of objects, attributes and events. This board is answer accuracy in percent on the Anticipation domain, predicting outcomes such as collisions, deformation and fluid flow; higher is better.
Metric: Answer accuracy (0-1 scaled to %) on the Anticipation domain (predicting physical outcomes such as collisions, deformation and fluid flow) of the image- and video-based questions with verified answers over real-world physical scenes; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o | 60.11 | #741 |
| 2 | GPT-4o Mini | 59.11 | #1623 |
| 3 | Gemini 2.5 Flash | 58.22 | #453 |
| 4 | InternVL3-78B | 58 | #738 |
| 5 | Phi-4 Multimodal Instruct | 55.33 | #3882 |
| 6 | Claude Sonnet 4 | 53.22 | #400 |
| 7 | Qwen 2 VL 7B | 52.22 | #2261 |
| 8 | Mistral Small 3.2 | 41 | #1591 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=causalphys-anticipation · How It Works · Data refreshed daily, snapshot 2026-11-13.