Wait Which Model?
← Back to directory
Google DeepMind

Gemma 4

Released Apr 2, 2026 · knowledge cutoff 2025-01

Status
Superseded
Location
United States / United Kingdom
Type
LLM
Modality
Multimodal
Context window
262K
Max output
—
Speed
35 tok/s · 0.98s to first answer token
Price ($/MTok in / out)
$0.10 / $0.34
Cost per task
$0.034
Open weights
Yes
Benchmarks5 of 10 reported

MMLU-Proretired

85.2%

GPQA Diamond

84.3%

AIME (latest)retired

89.2%

Humanity's Last Exam

19.5%

LMArena Elo

1452

SWE-bench Verified

—

SWE-bench Pro

—

Terminal-Bench 2.1

—

GDPval-AA v2

—

ARC-AGI-2

—
Strengths & weaknesses

Strengths

  • Dense rather than sparse — predictable latency and memory, no routing variance to debug
  • Fits on a single high-end consumer GPU once quantized
  • Native system-role support and a switchable thinking mode, both unusual at this size
  • Reliable instruction following, which makes it a good retrieval and pipeline component

Weaknesses

  • Full-precision serving still wants datacenter-class memory
  • No first-party hosted endpoint — you run it yourself or trust a third-party host
  • A component rather than an agent; it isn't built for long autonomous runs

Benchmarks shown are for the 31B Dense variant. LMArena Elo (~1452) and the MMLU-Pro/GPQA/AIME/HLE figures are third-party community-reported, not an official Google table (BenchLM lists GPQA Diamond as 85.7% and HLE as 26.5%, so treat these as approximate). Pricing $0.10/$0.34 per MTok is OpenRouter's listing for google/gemma-4-31b-it — there is no first-party Google API price (Google hosts it on the Gemini API and a Vertex model-as-a-service page exists for the 26B-A4B variant, but neither lists a per-token price for 31B), and other hosts differ (CoreWeave $0.12/$0.35, DeepInfra $0.13/$0.38 per Artificial Analysis). Weights were quietly published March 31, 2026; the formal Google blog announcement followed April 2, 2026. Knowledge cutoff (January 2025) confirmed via Google's official Gemma 4 model card (ai.google.dev). Output speed and time to first answer token are Artificial Analysis' Gemma 4 31B (Reasoning) figures on Google's API.

For developers

API model strings

Not researched

Licence

Apache License 2.0 · Permissive · commercial use permitted

Retirement

No retirement announced

Lineage

No recorded predecessor

News