{"slug":"agentbench","name":"AgentBench","category":"eval","categoryName":"Evaluation, red-teaming & guardrails","audience":["ai-era"],"primary":"ai-era","openClosed":"open","pricing":"open-source","license":"Apache-2.0","maintained":"stale","officialUrl":"https://github.com/THUDM/AgentBench","repo":"https://github.com/THUDM/AgentBench","latestVersion":"","latestRelease":"","stars":3784,"starsAsOf":"2026-10-22","description":"A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)","descriptionZh":"LLM 作为 agent 的综合基准","callMethods":["CLI"],"platforms":[],"addedAt":"2026-10-10","updatedAt":"2026-10-22","topics":["chatgpt","gpt-4","llm","llm-agent"],"language":"Python","lastPush":"2026-02-08","formerly":null,"packages":[],"recentVersions":[],"alternatives":["gorilla","vlmevalkit","promptfoo","ragas","opencompass","giskard-oss","osworld","tau2-bench"],"stacks":[],"scenarios":["evaluate-and-monitor"],"problems":[],"reasonZh":"开源大库收录：LLM 作为 agent 的综合基准","sources":["oss","github-pool"],"record":"https://aimap.page/api/v1/software/agentbench.json","pages":{"en":"https://aimap.page/en/software/agentbench/","zh-hans":"https://aimap.page/zh-hans/software/agentbench/"}}