CausaLab (7-Node SCMs): leaderboard
Metric: Reactor frequency accuracy (%; exact prediction of the held-out crystal's frequency, up to 50 hidden 7-node linear SCMs, 2 observations and 24 interventions, one run). Source: arxiv.org. Saturation forecast: Around June 2027. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 (High) | 64 |
| 2 | GPT-5 Mini | 16 |
Interactive version: theaggregate.ai/benchmark?slug=causalab-7-node-scms · How It Works · Data refreshed daily, snapshot 2026-09-26.