New Google model debuts at #14 and #32 on leaderboards, mocked vs Kimi and GLM

airesearch12 · x · 2026-09-03

Commenting on a new Google DeepMind release, the author says the scores aren't bad for its assumed size, but a brand-new model ranking #14 and #32 on leaderboards won't impress anyone — especially compared to Kimi and GLM. He asks when Google will deliver a new SOTA model.

Original post →

More from Models

Models channel →