FRAMEWIREIndonesiaUpdated Aug 15Live wire
0:00 / 0:00

Looks at this test of grok 4.6 vs qwen 3.8-27b wtf

WëscheAug 156
0:00 / 0:00

Four models, same scene.

Grok 4.6 finished last, behind Opus 5, Qwen 3.8 Max and GLM 5.3 Max. look at the clocks though. Grok finished in roughly 15 minutes. Opus took about 45. three times faster and fourth on looks. in a one-shot beauty contest that reads as a loss, and it is

88n77Aug 155
0:00 / 0:00

Qwen 3.8 Max Full COURSE 1 HOUR (Build & Automate Anything)

Julian Goldie SEOAug 151
0:00 / 0:00

The secret behind Qwen 3.8 27B is GRPO distillation using Qwen 3.8 Max outputs as the RL objective

Letting the smaller model reason as much as it needs to match the larger one.

0xMarioNawfalAug 1539