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
| # | Model | Score |
|---|---|---|
| 1 | GPT-6 | 46.3 |
| 2 | GPT-5.6 Sol | 37.9 |
| 3 | InternVL3.5-8B | 36.4 |
| 4 | Gemini 3.1 Pro (Preview) | 36.3 |
| 5 | Seed 2.1 Pro | 35.7 |
| 6 | Qwen 3 VL 8B Instruct | 33.4 |
| 7 | GPT-4o | 32.6 |
| 8 | Kimi K2.5 | 31.5 |
Interactive version: theaggregate.ai/benchmark?slug=causal-plan-bench-counterfactual-outcome · How It Works · Data refreshed daily, snapshot 2026-09-29.