Pinned Repositories
evals
Evals is a framework for evaluating OpenAI models and an open-source registry of benchmarks.
pekagi's Repositories
pekagi/evals
Evals is a framework for evaluating OpenAI models and an open-source registry of benchmarks.
Evals is a framework for evaluating OpenAI models and an open-source registry of benchmarks.
Evals is a framework for evaluating OpenAI models and an open-source registry of benchmarks.