Causal-Plan-Bench - Spatial Precondition: leaderboard
Metric: Accuracy (%) on the spatial precondition (conditions that must hold 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 2035. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-6 | 42 |
| 2 | Seed 2.1 Pro | 40 |
| 3 | Gemini 3.1 Pro (Preview) | 38 |
| 4 | GPT-5.6 Sol | 37 |
| 5 | InternVL3.5-8B | 36 |
| 6 | Kimi K2.5 | 32 |
| 7 | Qwen 3 VL 8B Instruct | 32 |
| 8 | GPT-4o | 30 |
Interactive version: theaggregate.ai/benchmark?slug=causal-plan-bench-spatial-precondition · How It Works · Data refreshed daily, snapshot 2026-09-29.