LM Evaluation Harness vs OpenAI Evals
| LM Evaluation Harness | OpenAI Evals | |
|---|---|---|
| Free plan | Yes | |
| Free trial | No | |
| Paid from | Free | |
| Platforms | api, Linux, self-hosted | api, self-hosted, Web |
| Deployment | self-hosted | hybrid |
| Deployment options | self-hosted | |
| Custom metrics | Yes | |
| Safety evaluations | Yes | Yes |
| Evaluation methods | basic exact/match evaluations, model-graded evaluations, custom evaluation logic, academic benchmarks, meta-evaluations | |
| Model support | OpenAI API models and custom CompletionFunction implementations | |
| Prompt versioning | Yes | |
| API access | Yes |
Listed together in Best AI LLM Evaluation Tools