CrashSight - Involved Parties: leaderboard
Involved-party questions (vehicle and vulnerable road user types, features and counts) of CrashSight (2026), a multiple-choice VQA benchmark on real roadside-camera traffic crash videos answered zero-shot from four frames. Accuracy in percent; higher is better.
Metric: Accuracy (%) on involved-party questions (vehicle and vulnerable-road-user types, features, counts), 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: Estimated already saturated. 6 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | InternVL3-8B | 58.1 | #1795 |
| 2 | LLaVA-NeXT-Video-7B | 52.3 | #5783 |
| 3 | InternVL3-2B | 52.1 | #3318 |
| 4 | Qwen 2.5 VL 7B Instruct | 51.9 | #1919 |
| 5 | Qwen 2.5 VL 3B Instruct | 50.6 | #2720 |
| 6 | LLaVA-OneVision-0.5B | 36 | #7977 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=crashsight-involved-parties · How It Works · Data refreshed daily, snapshot 2026-11-22.