CausalDS: leaderboard

Metric: CausalDS score (0 is perfect, lower is better, unbounded above; task-count-weighted sum of one minus the pass rate, the relative numeric error S_NR and the median F1 loss, on a 100-scene realistic exam of Pearl-ladder causal data-science tasks (28 associational, 51 interventional, 21 counterfactual) over SCM-generated data files, solved in the mini-swe-agent harness with at most 100 steps). Source: arxiv.org. Saturation forecast: Around October 2027. 6 models tracked.

Top models

#ModelScore
1Claude Opus 4.8 (High)0.28
2Gemini 3.1 Pro (Preview)0.37
3Qwen 3.6 35B A3B0.45
4Kimi K2.60.48
5GPT-5.5 (High)0.56
6Gemma 4 26B0.64

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