CausalPhys - Intervention: leaderboard

Metric: Answer accuracy (0-1 scaled to %) on the Intervention domain (reasoning under explicit manipulations such as viewpoint, spatial or temporal changes) of the image- and video-based questions with verified answers over real-world physical scenes; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 11 models tracked.

Top models

#ModelScore
1GPT-4o57.07
2InternVL3-78B57.07
3Claude Sonnet 456.72
4Gemini 2.5 Flash55.67
5GPT-4o Mini51.31
6Mistral Small 3.248.52
7Phi-4 Multimodal Instruct48.52
8Qwen 3 VL 32B47.99
9Qwen 2 VL 7B47.64

Interactive version: theaggregate.ai/benchmark?slug=causalphys-intervention · How It Works · Data refreshed daily, snapshot 2026-09-29.