Causal-Plan-Bench - Affordance Visual Semantics: leaderboard
A four-choice task of Causal-Plan-Bench (2026) on the manipulated object, interaction hotspot and physical mechanism in a keyframe, 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 affordance visual semantics (manipulated object, hotspot and mechanism in a keyframe) 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
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 35 | #94 |
| 2 | GPT-6 Astra | 35 | #6 |
| 3 | Seed 2.1 Pro | 33 | #135 |
| 4 | GPT-5.6 Sol | 32 | #30 |
| 5 | Qwen 3 VL 8B Instruct | 30 | #981 |
| 6 | GPT-4o | 29 | #741 |
| 7 | Kimi K2.5 | 27 | #256 |
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-affordance-visual-semantics · How It Works · Data refreshed daily, snapshot 2026-11-13.