WeaveBench - Desktop: leaderboard
Metric: PassRate (%) on the Desktop domain tasks of 114 long-horizon real-world computer-use tasks that need GUI, CLI, code and API tools together, each model run as the backbone of a fixed OpenClaw agent runtime with the full hybrid tool pool at its best thinking mode; higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 (High) | 55.6 |
| 2 | Claude Opus 4.7 (High) | 55.6 |
| 3 | GPT-5.5 (High) | 38.9 |
| 4 | GPT-5.3 Codex (High) | 33.3 |
| 5 | Gemini 3.1 Pro (Preview) | 0 |
| 6 | Qwen 3.5 397B A17B | 0 |
| 7 | Qwen 3 VL 8B (Thinking) | 0 |
| 8 | GPT-5.1 Codex (High) | 0 |
Interactive version: theaggregate.ai/benchmark?slug=weavebench-desktop · How It Works · Data refreshed daily, snapshot 2026-09-29.