MacAgentBench (OpenClaw) - Multi-App: leaderboard
The 140 cross-application workflows that combine several apps of MacAgentBench (Fu et al., 2026), run in a containerized macOS environment and scored by deterministic rule-based checks of the final state. Pass@1 in percent inside the OpenClaw agent harness, which adds shell, AppleScript and a skill library; higher is better.
Metric: Pass@1 (%; share of the 140 Multi-App tasks solved on a single attempt, deterministic rule-based checks; the OpenClaw in-container agent harness with shell, AppleScript and its skill library, at most 50 steps). Source: arxiv.org. Saturation forecast: Around February 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 | 63.6 | #100 |
| 2 | GPT-5.4 | 45 | #121 |
| 3 | Gemini 3.1 Pro (Preview) | 40 | #91 |
| 4 | Qwen 3 VL 235B A22B | 22.9 | #477 |
| 5 | Qwen 3 VL 32B (Thinking) | 5.7 | #557 |
| 6 | Qwen 3 VL 8B (Thinking) | 2.9 | #887 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=macagentbench-openclaw-multi-app · How It Works · Data refreshed daily, snapshot 2026-11-12.