CrashSight - Scene Identification: leaderboard

Scene identification questions (road type, lighting, weather, traffic context) 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 scene identification questions (road type, lighting, weather, traffic context), 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

#ModelScoreOverall rank
1LLaVA-NeXT-Video-7B75.5#5734
2InternVL3-8B72.4#1782
3InternVL3-2B71.8#3290
4Qwen 2.5 VL 7B Instruct67.7#1902
5Qwen 2.5 VL 3B Instruct66.8#2713
6LLaVA-OneVision-0.5B59.4#7956

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=crashsight-scene-identification · How It Works · Data refreshed daily, snapshot 2026-11-21.