X · @teortaxesTex
· X / Twitter
Really looking forward to V4F-0731 on new EQBench according to @tngtech, it seems roughly 200 ELO better on V3. It does feel much more alive
Really looking forward to V4F-0731 on new EQBenchaccording to @tngtech, it seems roughly 200 ELO better on V3.It does feel much more aliveSam Paech: Creative writing bench updates. We got:- kimi-k3- gpt-5.6- muse-spark-1.1- @thinkymachines first model InklingSo much healthy competition, love to see it!