Announcement
GPT-6 Sol tops the published TerminalBench-Fn leaderboard
A post announcing fidian’s TerminalBench-Fn leaderboard says GPT-6 Sol leads because models such as Astra and Fable refuse some cybersecurity tasks. It recommends GPT-6 Luna for value.
TLDR
The leaderboard announcement places GPT-6 Sol first and attributes its lead to models such as Astra and Fable refusing some cybersecurity tasks. The poster recommends GPT-6 Luna for value.
Combined views
134
2 Sources, first seen 3h ago
4 likes
