FGTR-Bench - Holistic Sign: leaderboard

The holistic traffic-sign subset of FGTR-Bench (2026): accuracy in percent on 1,447 4-option multiple-choice questions about traffic signs in the blind test split, zero-shot. Higher is better.

Metric: Accuracy (%) on 1,447 holistic traffic-sign 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

#ModelScoreOverall rank
1Qwen 2.5 VL 7B Instruct86.7#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-holistic-sign · How It Works · Data refreshed daily, snapshot 2026-11-13.