# AgentBench

AgentBench is an AI benchmark; this page records what it measures and traces its data, grader, and scores to primary sources.

Measures language-model agents across operating systems, databases, games, web shopping, and other interactive environments.

## Details

- Address: Online, Global
- Website: [github.com/THUDM/AgentBench](<https://github.com/THUDM/AgentBench>)
- Tags: Helpful, Science
- Category: Agents
- Status: Active
- Data licence: Apache-2.0
- Data access: open
- Grader: mixed
- Organization: THUDM
- Released: 2023-08
- Paper: [arxiv.org/abs/2308.03688](<https://arxiv.org/abs/2308.03688>)
- Repository: [github.com/THUDM/AgentBench](<https://github.com/THUDM/AgentBench>)
- Task count: 8
- Top-score provenance: unknown
- ABI family: No

## Questions

### Where is AgentBench?

AgentBench is at Online, Global.

### How do I contact AgentBench?

To contact AgentBench, visit https://github.com/THUDM/AgentBench.

## Source

From [Benchmark primary sources](https://aibenchmarkindex.com/about), license CC0-1.0, checked 2026-10-15.

Last updated October 15, 2026.

## Links

- This benchmark on the [web page](<https://aibenchmarkindex.com/global/online/agentbench>)
- [Agents in Online](<https://aibenchmarkindex.com/global/online/category/agents.md>)
- [More benchmarks in Online](<https://aibenchmarkindex.com/global/online.md>)

> **Check before you compare.** Benchmark methods and leaderboards change. Follow the cited primary source before using a result in a decision.