PAWBench (VLM Prediction) - Coverage: leaderboard
Metric: Coverage (%; PAWBench measures whether a system reproduces the reference distribution over physically possible outcomes across 50 rollouts on 25 scenarios per physical track from repeated VLM text predictions of the outcome, no video generation; valid-support recovery: share of reference-supported outcomes the model produces (%, higher is better; averaged over passing scenes)). Source: arxiv.org. Saturation forecast: Around 2029. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.5 Flash | 46.6 |
| 2 | Kimi K2.6 | 45.1 |
| 3 | GLM-5V Turbo | 39.9 |
| 4 | Qwen 3.5 Plus | 35.9 |
| 5 | GPT-5.5 | 34.3 |
Interactive version: theaggregate.ai/benchmark?slug=pawbench-vlm-prediction-coverage · How It Works · Data refreshed daily, snapshot 2026-09-26.