AgentBench vs DecodingTrust
AgentBench
github.com
DecodingTrust
decodingtrust.github.ioSide by side
| Figure | AgentBench | DecodingTrust |
|---|---|---|
| Price from | — | — |
| Free plan | — | — |
| Free trial | — | — |
| Open source | — | — |
| Linux | Yes | — |
| API | Yes | Yes |
| Self-hosted | Yes | Yes |
| Plans published | 0 | 0 |
| Spec score · LLM Evaluation Tools | 7.8 (#10) | 7.5 (#16) |
| License | The repository is licensed under Apache License 2.0. | The dataset and project are distributed under the CC BY-SA 4.0 license. |
| Purpose | AgentBench is a benchmark for evaluating the reasoning and decision-making abilities of LLMs acting as agents. | DecodingTrust is a research project for assessing trustworthiness in GPT models and helping researchers and practitioners understand their capabilities, limitations, and deployment risks. |
| Support | The project invites users to join its Slack for questions and collaboration, and lists a Google Group for questions about AgentBench FC. | The project invites questions at [email protected]. |
In their own words
DecodingTrust
DecodingTrust has no write-up on Specifiction yet; its figures are above.