weavebench/WeaveBench

[EMNLP 2026] WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces

语言：Python · GitHub 星标：175 · Fork：4

话题：agent-as-judge · benchmark · computer-use-agent · gui-agent · hybrid-interface · llm-evaluation

在 GitHub 上查看原仓库