Skip to content
The Nexus
TECHNOLOGYApr 27 · 12:35 UTCHACKER NEWSGodelNumbering

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

An open-source agent developed by the author achieved a 65.2% score on TerminalBench, outperforming Google's 47.8% and Junie CLI's 64.3%. The author emphasizes no cheating mechanisms were used and highlights issues with the leaderboard maintainers' response time.

Nexus surfaces and summarizes. The full story lives at the source.

Mentioned
Spot something wrong with this article?Report a problem →
Forward this