openai / evals
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
GitHub Repo 
41K
lines of main code
1.5K files
2.6K
lines of test code
52 files
5.8K
lines of other code
121 files
3y
age
1,199 days
<1%
main code touched
1 year (52 LOC)
0%
new main code
1 year (20 LOC)
29K
py
8.2K
yaml
JSONL
1.9K
jsonl
1.3K
ipynb
0.3K
html
0.1K
js
IN
0.01K
in
30 days 90 days all time 2026 2024 2023
+0
-0
+5
-5
+60K
-5.5K
+5
-5
+32K
-1.1K
+27K
-4.4K
0 1 1.9K

1

419

1.5K

0 1 599

1

38

560

0 1 426

1

15

417

2026 2024 2023

generated by sokrates.dev (configuration) on 2026-06-24