Causal-Plan-Bench - Spatial Precondition: leaderboard
A four-choice task of Causal-Plan-Bench (2026) on the spatial conditions (proximity, contact, space) that must hold before an observed action starts, 100 held-out video items scored by accuracy (%). Items come from egocentric and robot video and every model sees the same instruction and evidence; higher is better.
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 2031. 14 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra | 42 | #6 |
| 2 | Seed 2.1 Pro | 40 | #135 |
| 3 | Gemini 3.1 Pro (Preview) | 38 | #94 |
| 4 | GPT-5.6 Sol | 37 | #30 |
| 5 | Kimi K2.5 | 32 | #256 |
| 6 | Qwen 3 VL 8B Instruct | 32 | #981 |
| 7 | GPT-4o | 30 | #741 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=causal-plan-bench-spatial-precondition · How It Works · Data refreshed daily, snapshot 2026-11-13.