openbench

Same model, different wrapper: a from-scratch benchmark comparing coding-agent harnesses (codex, pi, opencode, cursor, devin) and open models on correctness, speed, and token cost

minghinmatthewlam/openbench

View on GitHub ↗

Same model, different wrapper: a from-scratch benchmark comparing coding-agent harnesses (codex, pi, opencode, cursor, devin) and open models on correctness, speed, and token cost

openbench grew +1.5% in the last 30 days, ranks 529th of 738 in Evaluation & Guardrails, last commit 58 days ago.

Star trajectory

93 days tracked
2026-07-24138 stars today2026-10-25
Momentum

+1.5% in 30d, above the Evaluation & Guardrails median of +1.2%.

Maintenance

Last commit 58 days ago, staler than the median of 15d.

How it compares in Evaluation & Guardrails

openbench
138
stars
+1.5% 30d
commit 58 days ago
Evaluation & Guardrails median
245.5
stars
+1.2% 30d
commit ~15d ago
Leader · WeKnora
35.3k
stars
+18.5% 30d
commit today

Ranked 529th of 738 by stars.

Language
Python
License
MIT License
Contributors
3
Forks
10
Watchers
0
Open issues
7
Releases
2
Created
2026-06-19
Stars this week
+1

You've seen where openbench stands today.

Get the moves before everyone else: the 5 Evaluation & Guardrails repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain openbench?

Claim this page to add your own call-to-action.

Claim this page