CausalPhys - Entity Faithfulness: leaderboard
Metric: Entity Faithfulness (0-1 scaled to %), the share of causal-graph entities the rationale mentions, 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 March 2028. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | InternVL3-78B | 69.68 |
| 2 | GPT-4o | 67.95 |
| 3 | Qwen 3 VL 32B | 67.95 |
| 4 | GPT-4o Mini | 66.52 |
| 5 | Claude Sonnet 4 | 66.34 |
| 6 | Gemini 2.5 Flash | 65.97 |
| 7 | Mistral Small 3.2 | 62.87 |
| 8 | Phi-4 Multimodal Instruct | 62.26 |
| 9 | Qwen 2 VL 7B | 58.71 |
Interactive version: theaggregate.ai/benchmark?slug=causalphys-entity-faithfulness · How It Works · Data refreshed daily, snapshot 2026-09-29.