Open-weight 27B hits 38% on Terminal-Bench 2.0 (Opus 4.1 hit 38% in Aug 2025)antigma.ai6 points·by ubermon·3 mesi fa·9 comments
ubermon·3 mesi fa·discussTotally agree! I think we are very early on discovering the full potential of local models
ubermon·3 mesi fa·discussThank you! I think there is a lot to dive deep later with different hardware, inference engine, prompt/harness setup etc.