FGTR-Bench - Road Participants: leaderboard
The road-participant subset of FGTR-Bench (2026): accuracy in percent on 1,200 4-option multiple-choice questions about road participants, including distant ones, zero-shot. Higher is better.
Metric: Accuracy (%) on 1,200 road-participant questions, 4-option multiple-choice questions on the blind test split, zero-shot (models without FGTR-Bench training), greedy letter decoding; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2.5 VL 7B Instruct | 51.3 | #1833 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=fgtr-bench-road-participants · How It Works · Data refreshed daily, snapshot 2026-11-13.