CausalPhys - Goal Orientation: leaderboard
Metric: Answer accuracy (0-1 scaled to %) on the Goal-Orientation domain (counterfactual choice of actions that achieve a desired outcome) of the image- and video-based questions with verified answers over real-world physical scenes; higher is better. Source: arxiv.org. Saturation forecast: Around 2030. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 58.78 |
| 2 | InternVL3-78B | 57.99 |
| 3 | Gemini 2.5 Flash | 54.39 |
| 4 | Qwen 3 VL 32B | 51.72 |
| 5 | GPT-4o Mini | 51.57 |
| 6 | Qwen 2 VL 7B | 49.06 |
| 7 | Mistral Small 3.2 | 47.96 |
| 8 | Claude Sonnet 4 | 47.02 |
| 9 | Phi-4 Multimodal Instruct | 44.83 |
Interactive version: theaggregate.ai/benchmark?slug=causalphys-goal-orientation · How It Works · Data refreshed daily, snapshot 2026-09-29.