X · @togethercompute
· X / Twitter
We analyzed GLM 5.2 vs Sonnet 5 for software engineering tasks using DeepSWE. GLM 5.2 gets you ~80% of Sonnet 5's capability at ~20% of the price. Mor…
We analyzed GLM 5.2 vs Sonnet 5 for software engineering tasks using DeepSWE.GLM 5.2 gets you ~80% of Sonnet 5's capability at ~20% of the price. More insights in the thread!Zain: Deepdive: Sonnet 5 and GLM-5.2 on DeepSWE> both max reasoning effort> on full DeepSWE benchmark 113 original long-horizon SWE tasks> 4 trial