iOSWorld (Vision-Only): leaderboard

Metric: Task pass rate (%) over all 133 tasks under vision-only input, GPT-5.4-Mini trajectory judge, 50-step budget; higher is better. Source: arxiv.org. Saturation forecast: Around 2028. 6 models tracked.

Top models

#ModelScore
1Claude Sonnet 4.628.6
2Gemini 3 Flash27.8
3Claude Opus 4.626.3
4GPT-5.4 Mini26.3
5GPT-5.420.3
6Qwen 3.5 35B A3B12.8

Interactive version: theaggregate.ai/benchmark?slug=iosworld-vision-only · How It Works · Data refreshed daily, snapshot 2026-09-29.