Updates on existing evals; readmes; solvers - Githubissues

openai / evals

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

Other

14.36k stars 2.55k forks source link

Updates on existing evals; readmes; solvers #1483

Closed ojaffe closed 3 months ago

ojaffe commented 3 months ago

Miscellaneous updates:

Updates existing evals with
- Better READMEs
- Previously missed reproducibility code
- Minor bugfixes / improvements
- Improvements to solvers
- Update default solvers to use latest models
- Improved features and robustness for OAI solvers
- Features for applying postprocessors to solver outputs
- Fixed "completion_fn not found" warning from registry