MobileJudgeBench (SPA-Bench Judge): leaderboard

Metric: Judge accuracy (%; share of 931 human-annotated mobile-agent trajectories, from 6 benchmarks, 4 agent models and 68 apps, whose success or failure the judge classifies correctly; the SPA-Bench judge adapted to mobile trajectories, greedy decoding). Source: arxiv.org. Saturation forecast: Estimated already saturated. 5 models tracked.

Top models

#ModelScore
1GPT-5 Mini90.6
2Gemini 3 Flash (Preview)89.8
3Claude Sonnet 4.584.7
4GLM-4.6V82.2
5Qwen 2.5 VL 72B Instruct80.1

Interactive version: theaggregate.ai/benchmark?slug=mobilejudgebench-spa-bench-judge · How It Works · Data refreshed daily, snapshot 2026-09-26.