NoisyCausal - Value Perturbation: leaderboard
Causal reasoning under structured noise (NoisyCausal; Xu and Fu, 2026), value perturbation condition: random 3-7 variable causal graphs are grounded in medicine, education or economics scenarios and the model answers an interventional, counterfactual or attributional question whose answer follows from the clean model, with randomly altered variable values in the story. Accuracy in percent, higher is better.
Metric: Accuracy (%; synthetic structural-causal-model questions with randomly altered variable values). Source: arxiv.org. Saturation forecast: Estimated already saturated. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4 | 60.4 | #996 |
| 2 | GPT-3.5 | 54.2 | #2430 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=noisycausal-value-perturbation · How It Works · Data refreshed daily, snapshot 2026-11-12.