ObsDriveBench - Risk-aware Decision-making: leaderboard
Metric: Accuracy (%; dimension average of risk identification, fallback action and trajectory evaluation; multiple-choice questions on synchronized camera, LiDAR BEV and radar BEV inputs from K-Radar under fog, rain, snow and low light, answers matched by an LLM judge; official inference settings). Source: arxiv.org. Saturation forecast: Around December 2026. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 80.22 |
| 2 | Qwen 3 VL 32B | 79.71 |
| 3 | Qwen 2.5 VL 7B | 67.51 |
| 4 | GPT-5 | 66.8 |
| 5 | InternVL3-8B | 64.75 |
| 6 | InternVL3-38B | 57.9 |
Interactive version: theaggregate.ai/benchmark?slug=obsdrivebench-risk-aware-decision-making · How It Works · Data refreshed daily, snapshot 2026-09-29.