Robin Bilgil(@RBilgil):We really need to talk about time-per-task for open models Here's similar aggregated runs on @whirl_sh: 5.6 Luna spends <1m per task to GLM-5.3 flash's 6m avg, for IMO very similar real world performance. From early tests MiMo v2.6 is a step in the wrong direction too

Robin Bilgil

@RBilgil

Building @whirl_sh — AI orchestration layer for operations. ex-@monzo, @Citymapper

加入 April 2011

800 正在關注 1K 粉絲

Robin Bilgil@RBilgil

2026.09.22 11:13

We really need to talk about time-per-task for open models Here's similar aggregated runs on @whirl_sh: 5.6 Luna spends <1m per task to GLM-5.3 flash's 6m avg, for IMO very similar real world performance. From early tests MiMo v2.6 is a step in the wrong direction too