Causal-Plan-Bench - Failure Recovery: leaderboard

Metric: Open-ended failure recovery (a strategy to re-establish the conditions after a failure) 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-646.4
2Gemini 3.1 Pro (Preview)42.2
3Seed 2.1 Pro40.2
4GPT-5.6 Sol39.5
5Kimi K2.539.4
6GPT-4o38.2
7Qwen 3 VL 8B Instruct35.5
8InternVL3.5-8B34.7

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