Entry 2026-04-02
Open models keep closing the gap
Last verified 2026-07-22 · Primary source
Gemma 4 launched on April 2 with four variants; Google subsequently added a 12B model. The current family has five sizes: E2B, E4B, 12B, 26B A4B, and 31B. All use Apache 2.0 — a real license change from Google's previous, more restrictive terms for open models.
The 31B dense model hit #3 on Arena AI's text leaderboard at 1452 Elo, outperforming models twenty times its size. The 26B MoE hit #6 at 1441 Elo.
All variants support text and images; audio is supported by E2B, E4B, and 12B. The family also supports variable aspect ratios, document parsing, and handwriting OCR. Context limits vary by size, with up to 256K on the larger variants. Over 140 languages.
The gap between open and closed models compresses with every release. Self-hosted agents running Gemma 4 31B are now competitive on reasoning benchmarks with frontier models from a year ago. For teams that can't send code to an API, that matters.