WildRoadBench - Drainage Damage: leaderboard

Metric: F1 (%) of predicted boxes at IoU 0.5 for the drainage damage scene class (22 ground-truth boxes), VLM Track, zero-shot box grounding on the full 1,061-image aerial set (1,394 ground-truth boxes); higher is better. Source: arxiv.org. Saturation forecast: Around March 2027. 25 models tracked.

Top models

#ModelScore
1Qwen 3.6 Plus58.3
2Gemini 3 Pro57.8
3Gemini 3.1 Flash Lite50
4Qwen 3 VL 8B Instruct45.5
5Claude Sonnet 4.642.3
6Kimi K2.535.1
7Qwen 2.5 VL 7B Instruct23.8
8Gemini 2.5 Flash22.7
9GPT-5.4 (2026-03-05)21.7
10InternVL3-8B18.2
11GPT-4o (2024-05-13)18.2
12InternVL3-14B17.8
13Claude Opus 4.613.5
14Qwen 3 VL 8B (Thinking)12.2
15InternVL2-8B0

Interactive version: theaggregate.ai/benchmark?slug=wildroadbench-drainage-damage · How It Works · Data refreshed daily, snapshot 2026-10-07.