MacAgentBench: leaderboard
Metric: Pass@1 (%; share of the 676 macOS desktop tasks in 25 applications solved on a single attempt, judged by deterministic rule-based state checks; the benchmark's baseline pure-GUI agent (screenshots and mouse/keyboard actions only), at most 50 steps). Source: arxiv.org. Saturation forecast: Around May 2027. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 | 58.4 |
| 2 | Claude Opus 4.6 | 39.2 |
| 3 | Gemini 3.1 Pro (Preview) | 34.2 |
| 4 | Qwen 3 VL 235B A22B | 21.6 |
| 5 | Qwen 3 VL 32B (Thinking) | 21.3 |
| 6 | Qwen 3 VL 8B (Thinking) | 14.5 |
| 7 | uitars-1.5-7B | 9.8 |
Interactive version: theaggregate.ai/benchmark?slug=macagentbench · How It Works · Data refreshed daily, snapshot 2026-09-26.