{"id":"agentbench","name":"AgentBench","maker":"Tsinghua University (THUDM)","url":"https://github.com/THUDM/AgentBench","repo":"THUDM/AgentBench","summary":"A benchmark that evaluates language models as agents across several interactive environments.","details":"Covers environments such as operating system tasks, databases, a knowledge graph, web shopping and web browsing, each scored by task success. The repository holds the framework and datasets under Apache 2.0.","open_source":true,"hosted":false,"verified":"2026-11-15","category":"benchmarks","category_name":"Agent benchmarks","page":"https://modelmoot.com/tools/agentbench","reviewed":"2026-11-15","checked":{"at":"2026-11-15T13:03:28.711Z","address_answers":true,"repository":{"at":"2026-11-15T13:03:28.711Z","archived":false,"licence":"Apache-2.0","language":"Python","last_change":"2026-02-08T17:01:05.000Z","latest_release":null}},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}