CausalPhys - Relation Awareness: leaderboard

Metric: Relation Awareness (0-1 scaled to %), the share of directed causal dependencies the rationale captures, averaged over the four domains; the model writes a rationale and an answer; a GPT-4o judge makes binary checks of the rationale against the expert-annotated causal graph (typed object, attribute and event nodes with directed dependencies); higher is better. Source: arxiv.org. Saturation forecast: Around 2031. 11 models tracked.

Top models

#ModelScore
1InternVL3-78B30.52
2Qwen 3 VL 32B29.14
3Claude Sonnet 427.83
4GPT-4o27.6
5Mistral Small 3.226.41
6GPT-4o Mini24.68
7Gemini 2.5 Flash24.37
8Phi-4 Multimodal Instruct21.66
9Qwen 2 VL 7B20.02

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