AgentBench vs WebArena
AgentBench
github.comWebArena
webarena.devSide by side
| Figure | AgentBench | WebArena |
|---|---|---|
| Price from | — | — |
| Free plan | — | — |
| Free trial | — | — |
| Open source | — | — |
| Linux | Yes | — |
| API | Yes | — |
| Self-hosted | Yes | Yes |
| Plans published | 0 | 0 |
| Spec score · LLM Evaluation Tools | 7.8 (#10) | 6.8 (#26) |
| License | The repository is licensed under Apache License 2.0. | The WebArena code repository identifies its license as Apache-2.0. |
| Purpose | AgentBench is a benchmark for evaluating the reasoning and decision-making abilities of LLMs acting as agents. | WebArena is a standalone, self-hostable web environment and benchmark for building autonomous agents. |