ObviousBench

PUBLIC MODEL RELIABILITY · LAB VIEW

Google

52 public configurations across 17 model families in the 2026-07-25 release. The global cost frontier stays available as context.

GLOBAL REFERENCE RETAINED

Where Google sits in the complete public field

The lab is highlighted without changing the frontier calculation or zoom. This preserves the comparison frame that a provider-only chart would otherwise hide.

Google in the global fieldAll 432 public configurations on the same global log-cost and pass3 scale as the homepage frontier. Public field GoogleGlobal Pareto
Google configurations highlighted in the global ObviousBench cost and reliability field 100% 95% 90% 80% 60% 40% 20% 10% More expensive Cheaper

This is a fixed global reference, not a recomputed Google frontier.

CURATED DETAIL

Decision pages for Google

These highlighted cards have an indexable evidence page. The rest remain in the full explorer rather than being turned into thin pages.

FULL LAB VIEW

All observed Google model families

Sorted by highest observed answer pass3, then the lowest cost at that score. Release dates are not inferred because this release data does not encode a consistent vendor release-date field.

Gemma 4 31B ITBest observed 100% · $0.0251 Gemini 3.5 FlashBest observed 100% · $0.9955
Gemini 3.1 Pro PreviewBest observed 100% · $1.002
Gemini 3.6 FlashBest observed 100% · $1.317
Gemini 3 Flash PreviewBest observed 99.3% · $0.2473
Gemini 3.1 Flash LiteBest observed 97.9% · $0.1954
Gemini 3.5 Flash-LiteBest observed 97.9% · $0.51
Gemini 2.5 ProBest observed 97.2% · $1.702
Gemma 4 26B A4B ITBest observed 96.5% · $0.03507
Gemini 2.5 FlashBest observed 94.4% · $0.1852
Gemini 2.5 Flash LiteBest observed 88.2% · $0.03752
Gemma 3 12B ITBest observed 57.6% · $0.001058
Gemma 3 27B ITBest observed 50.7% · $0.001077
Gemma 2 27B ITBest observed 45.1% · $0.01551
Gemma 3n E4B ITBest observed 44.4% · $0.001682
Gemma 2 9BBest observed 42.4% · $0.001887
Gemma 3 4B ITBest observed 36.1% · $0.001003