Causal-Plan-Bench - Counterfactual Outcome: leaderboard

Metric: Open-ended counterfactual outcome (the consequence if a key condition fails) task, rubric score (0-100): a blind GPT-5.6-sol judge scores each open-ended answer against a human-verified reference from 0 to 1, times 100; 100 held-out expert-reviewed items per task drawn from egocentric and robot video (EPIC-KITCHENS, Ego4D, HoloAssist and others), the same instruction, visual evidence and answer format for every model, temperature 0.2, mean of three regenerated runs; higher is better. Source: arxiv.org. Saturation forecast: Around 2035. 14 models tracked.

Top models

#ModelScore
1GPT-646.3
2GPT-5.6 Sol37.9
3InternVL3.5-8B36.4
4Gemini 3.1 Pro (Preview)36.3
5Seed 2.1 Pro35.7
6Qwen 3 VL 8B Instruct33.4
7GPT-4o32.6
8Kimi K2.531.5

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