Library/simple-evals
Library/simple-evalsForked

openai/simple-evals

simple-evals

Simple-evals is OpenAI's framework for evaluating language models through standardized benchmarks and tests.

Builder

OpenAI

OpenAI

openai • ai-lab

Stars

4,424

Using upstream star count

Forks

481

Using upstream fork count

Open Issues

0

Activity Score

0/100

0 commits in 30d

Created

Apr 11, 2024

Project creation date

README Summary

Simple-evals is OpenAI's framework for evaluating language models through standardized benchmarks and tests. It provides a collection of evaluation scripts and tools to assess model performance across various tasks including reasoning, knowledge, and safety measures. The framework is designed to be easily extensible and reproducible for consistent model evaluation.

AI Dev Skills

Unmapped

Model EvaluationBenchmarkingPerformance AssessmentAI Testing

Tags

Model EvaluationBenchmarkingPerformance AssessmentAI TestingCloud APIAI Safety TestingBenchmark DevelopmentSafety AssessmentModel Comparison TestingModel ComparisonPerformance MeasurementAI Model BenchmarkingTextPerformance EvaluationAI SafetySelf-hostedPython

Taxonomy

Recent Activity

Updated 8 months ago

7 Days

0

30 Days

0

90 Days

0

Quality

prototype
Quality
medium
Maturity
prototype

Categories

Safety & AlignmentPrimaryOther AI / MLEvals & Benchmarking

PM Skills

Developer Platform

Languages

Python100.0%

Timeline

Project created
Apr 11, 2024
Forked
Mar 14, 2026
Your last push
8 months ago
Upstream last push
8 months ago
Tracked since
Jul 31, 2025

Similar Repos

pgvector cosine similarity · $0

Loading…