CausalPhys - Perception: leaderboard

Metric: Answer accuracy (0-1 scaled to %) on the Perception domain (association rung: recognizing objects and physical attributes) 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
1InternVL3-78B62.57
2GPT-4o Mini59.83
3Gemini 2.5 Flash59.2
4GPT-4o58.89
5Claude Sonnet 458.68
6Qwen 3 VL 32B56.89
7Phi-4 Multimodal Instruct55.73
8Qwen 2 VL 7B52.05
9Mistral Small 3.248.26

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