FRAMEWIREIndonesiaUpdated Sep 3Live wire
0:00 / 0:00

The big showdown documented

All based on forensic analysis of all 6 runs - multiple hours of zcode session materials Milions of tokens. Qwen 3.8 27b, Qwen 3.6 35B A3B, Ornith 1.5 35B A3B and Gemma 4 26B A4B All analyzed and compared All 4 bit All on a M2 Max Macbook Pro

Chris WSep 3
0:00 / 0:00

COMPETITION 1 RESULTS: — I would actually argue Muse Spark 1.3 could be tied with Qwen 3.8 Max given cost and speed…

My verdict is that GLM 5.3 is all around best when balancing performance on this visual task, cost, speed and token usage. Muse Spark 1.3 was insanely cheap

CuthSep 38
0:00 / 0:00

Playing Grok Bot has become a bit addictive recently, but the cycle credit is quickly used up.

I just happened to discover a treasure platform called FlatKey today, and it is currently doing an event and has free models for free🔥🔥🔥. So I asked Grok Bot to help me set up a dedicated Agent first, and let all the models called by this Agent use FlatKey. This platform only requires an API Key to call 100…

AI少年Sep 320
0:00 / 0:00

Finally, we have Qwen 3.8 Max.

This is the highest quality but took about an hour. It cost $5.58 and 212k tokens. It was extremely thorough and did the job well. Not sure if I would consider it the winner due to the time and cost... But if you really want a model to be thorough

CuthSep 3