News for hackers. Stuff that matters.

A comment on Show HN: OSS Agent I built topped the TerminalBench on Gemini-3-flash-preview.

Re:Show HN: OSS Agent I built topped the TerminalBench on Ge... by snqb on Monday April 27, 2026 @09:50AM (#47921550)
how well does it do on frontier models like Opus 4.6?
[ Parent | on HN ]
Re:Show HN: OSS Agent I built topped the TerminalBench on Ge... by GodelNumbering on Monday April 27, 2026 @10:10AM (#47921844)
I have only done functionality testing, no benchmark testing on Opus (decided to pay my rent instead)
[ Parent | on HN ]