Causal-Plan-Bench - Affordance Visual Semantics: leaderboard
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 2036. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 35 |
| 2 | GPT-6 | 35 |
| 3 | InternVL3.5-8B | 33 |
| 4 | Seed 2.1 Pro | 33 |
| 5 | GPT-5.6 Sol | 32 |
| 6 | Qwen 3 VL 8B Instruct | 30 |
| 7 | GPT-4o | 29 |
| 8 | Kimi K2.5 | 27 |
Interactive version: theaggregate.ai/benchmark?slug=causal-plan-bench-affordance-visual-semantics · How It Works · Data refreshed daily, snapshot 2026-09-29.