alt Hacker NewsArtificialAnalysis puts out benchmarks for harnesses now as well, and OpenCode seems to be winning it. https://artificialanalysis.ai/agents/coding-agents#coding-ag...
I only found this yesterday, and it inspired me to start testing out OpenCode.
Replies
dmix • today at 1:23 PM
I'm not surprised to also see Cursor above Claude code, their harness is very good.
➕ show 1 reply
bensyverson • today at 1:30 PM
Can OpenCode dispatch background subagents yet? I tried it a week ago and saw nothing. This is 99% of my workflow at this point.
➕ show 2 replies
arational • today at 2:19 PM
[dead]
Just a warning, this is on Opus. There's not a clear harness winner. It will change depending on the models.