Causal-Plan-Bench - Strategic Rationale: leaderboard

Metric: Open-ended strategic rationale (why the step serves the high-level goal) 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 2033. 14 models tracked.

Top models

#ModelScore
1GPT-643
2Gemini 3.1 Pro (Preview)35.2
3Kimi K2.532.7
4GPT-5.6 Sol32
5GPT-4o27.6
6Seed 2.1 Pro26.2
7InternVL3.5-8B25.2
8Qwen 3 VL 8B Instruct23.5

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