Kimi K3 beats GLM 5.2 on 100 deep-research tasks, but costs 5x more

AravSrinivas · x · 2026-07-24

We benchmarked Kimi K3 and GLM 5.2 on 100 deep-research tasks from DRACO (via Perplexity) and had Fable judge the results.

The thread says K3 scored much higher, but GLM was substantially faster and cheaper. A full deep-dive thread is linked in the original post.

Original post →

More from Models

Models channel →