NoisyCausal - Causal Swap: leaderboard
Metric: Accuracy (%; synthetic structural-causal-model questions with the values of causally linked variables swapped). Source: arxiv.org. Saturation forecast: Around December 2026. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4 | 50.1 |
| 2 | GPT-3.5 | 44.7 |
Interactive version: theaggregate.ai/benchmark?slug=noisycausal-causal-swap · How It Works · Data refreshed daily, snapshot 2026-09-26.