ObsDriveBench - Observability Awareness: leaderboard
Metric: Accuracy (%; dimension average of modality-specific observability, cross-modal comparison and cross-modal verification; 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 2032. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 54.72 |
| 2 | InternVL3-8B | 44.8 |
| 3 | Qwen 2.5 VL 7B | 43.74 |
| 4 | GPT-5 | 41.89 |
| 5 | Qwen 3 VL 32B | 41.44 |
| 6 | InternVL3-38B | 40.82 |
Interactive version: theaggregate.ai/benchmark?slug=obsdrivebench-observability-awareness · How It Works · Data refreshed daily, snapshot 2026-09-29.