DriveCombo-Text - L4 Static and Dynamic Rules: leaderboard
Metric: Accuracy (%) on DriveCombo Level 4 (a static and a dynamic rule together) four-option multiple-choice questions on the 20% test split, rules from five countries' traffic codes; text-only variant in which the frames are replaced by a textual scene description; zero-shot, greedy decoding; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 14 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 Pro | 75.78 | #75 |
| 2 | Claude Sonnet 4.5 | 74.38 | #138 |
| 3 | Gemini 2.5 Pro | 73.76 | #145 |
| 4 | GLM-4.5V | 71.94 | #339 |
| 5 | Gemini 2.5 Flash | 69.33 | #237 |
| 6 | Gemma 3 27B | 67.55 | #596 |
| 7 | GPT-5 Mini | 66.95 | #176 |
| 8 | GPT-5 Nano | 66.82 | #415 |
| 9 | Gemma 3 12B | 56.56 | #666 |
| 10 | Gemma 3 4B | 48.16 | #1084 |
| 11 | Llama 3.2 11B | 45.59 | #1183 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=drivecombo-text-l4-static-and-dynamic-rules · How It Works · Data refreshed daily, snapshot 2026-10-11.