Illustration drawn by RepoMasters from the repo’s ID and its language color. Credits
PrototypeCommon

minghinmatthewlam/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

Owner
minghinmatthewlam (personal account)
Stars
Stars: 137
Forks
Forks: 10
Language
Python
License
MIT
Created
2026
Topics
ai-agentsbenchmarkcoding-agentsevalsllmopen-models
Tier
Prototype (100 to 249 ★) What this tier means
View on GitHub

More repos by minghinmatthewlam

All 2 repos by minghinmatthewlam

Nearby in Python

All Python repos