CrashSight: leaderboard
Metric: Accuracy (%) on all seven question categories (the paper's AVG), four-option multiple-choice VQA on held-out roadside-camera crash videos of CrashSight-VQA (4 frames at 1 fps, zero-shot, deterministic decoding, exact letter match); higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | InternVL3-8B | 68.7 |
| 2 | Qwen 2.5 VL 7B Instruct | 62.9 |
Interactive version: theaggregate.ai/benchmark?slug=crashsight · How It Works · Data refreshed daily, snapshot 2026-10-07.