SWE-bench/SWE-bench
▲ +40 ★ this week
SWE-bench: Can Language Models Resolve Real-world Github Issues?
CL-bench: A Benchmark for Context Learning
$ git clone https://github.com/Tencent-Hunyuan/CL-bench.git▲ +40 ★ this week
SWE-bench: Can Language Models Resolve Real-world Github Issues?
▲ +1 ★ this week
中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard
▲ +7 ★ this week
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Z-Bench 1.0 by 真格基金:一个麻瓜的大语言模型中文测试集。Z-Bench is a LLM prompt dataset for non-technical users, developed by an enthusiastic AI-focused team in Zhenfund.
▲ +10 ★ this week
OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks
▲ +3 ★ this week
CVE-Bench: A Benchmark for AI Agents’ Ability to Exploit Real-World Web Application Vulnerabilities
Data from GitHub · snapshot Nov 16, 2026