PAWBench (VLM Prediction) - Calibration: leaderboard
Metric: Conditional total-variation distance for vision-language models predicting outcomes as text without video generation, times 100, on a 0 to 100 scale (0-100); lower is better; PAWBench measures whether a system reproduces the reference distribution over physically possible outcomes across 50 rollouts on 25 scenarios per physical track, averaged over scenes that pass the readability gate. Source: arxiv.org. Saturation forecast: Around August 2028. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GLM-5V Turbo | 34.8 |
| 2 | Kimi K2.6 | 38.2 |
| 3 | Gemini 3.5 Flash | 39.4 |
| 4 | Qwen 3.5 Plus | 40.9 |
| 5 | GPT-5.5 | 42.3 |
Interactive version: theaggregate.ai/benchmark?slug=pawbench-vlm-prediction-calibration · How It Works · Data refreshed daily, snapshot 2026-09-26.