Gemma 4 31B

Gemma moved to Apache-2.0 with this generation.

Released

Apr 2, 2026

Price in / out

—

Blended $/1M

—

Context

256K

Parameters: 31B. License: Apache-2.0.

Benchmark scores

Benchmark	Score	Δ vs prior	Rank (current)	Configuration	Source
SWE-bench Verified	52%	—	#8 of 8	per Qwen's comparison table · leaderboard	morphllm.com ↗
Humanity's Last Exam	26.5%	—	#14 of 14	leaderboard	benchlm.ai ↗
τ²-bench (Telecom)	59.9%	—	#8 of 9	leaderboard	benchlm.ai ↗
MMLU-Pro	85.2%	—	#3 of 3	leaderboard	benchlm.ai ↗
Artificial Analysis Intelligence Index	29.4	—	#8 of 10	leaderboard	benchlm.ai ↗

Compare

Open the Comparison Lab with Gemma 4 31B and its open-weight peers pre-selected, then toggle any benchmark or model.

Every Gemma version over time

Shipping with it?

Benchmarks are a starting point. If you run Gemma 4 31B in production, post what it does well and where it falls over; other founders are deciding right now.

Write about Gemma 4 31B

Current open-weight peers

All

gpt-oss-120bOpenAI Muse Glimmer 30BMeta DeepSeek V4.1 Flash$0.14 in DeepSeek V4 Pro$0.435 in Kimi K3$3 in Kimi K2.7 Code$0.6 in