Causal-Plan-Bench - Affordance Precondition: leaderboard

Metric: Accuracy (%) on the affordance precondition (functional object properties needed before the action) task (four-choice accuracy (%) after answer normalization); 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 2034. 14 models tracked.

Top models

#ModelScore
1GPT-647
2Gemini 3.1 Pro (Preview)45
3Seed 2.1 Pro44
4Qwen 3 VL 8B Instruct41
5GPT-5.6 Sol40
6InternVL3.5-8B40
7GPT-4o39
8Kimi K2.535

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