Google: Gemma 4 26B A4B

google/gemma-4-26b-a4b-it

Context: 262,144In: $0.07/1MOut: $0.34/1MUpdated 2026-08-05

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

Intelligence
25.7
Coding
39.3
Agentic
11.0

Metric profile

Trend over time

Intelligence
25.7
Coding
39.3
Agentic
11.0

Only 1 snapshot so far (data refreshes daily) — the trend line appears after the 2nd snapshot.