Gemma 4 27B Benchmarks, Pricing & Rankings
Google · 2026-07-24 · Open · Current
Snapshot 2026-10-14 · updated weekly
Gemma 4 27B ranks #35 of 42 on the AMR leaderboard.
Gemma 4 27B benchmark scores
| GPQA Diamond | 67.4% | |
| MMLU-Pro | 66.1% | |
| SWE-Bench Verified | 36.8% | |
| AIME 2025 | 63.2% | |
| LiveCodeBench v6 | 53.9% | |
| Arena Elo | 1301 |
Gemma 4 27B price, speed & context
Input price
$0.18
per 1M tokens
Output price
$0.70
per 1M tokens
Speed
174
tok/s
Context
256K
tokens
About Gemma 4 27B
Gemma 4 27B is Google’s open small-model line for on-device and edge deployment, with the widest fine-tune tooling of any open family.
Models around Gemma 4 27B in the rankings
More Google models
Gemma 4 27B FAQ
Where does Gemma 4 27B rank?
Gemma 4 27B ranks #35 of 42 tracked AI models on the AMR aggregate as of October 2026, with an aggregate score of 72.0. Its strongest dimension is GPQA Diamond at 67.4%.
How much does Gemma 4 27B cost?
Gemma 4 27B costs $0.18 per million input tokens and $0.70 per million output tokens on the standard API. At a typical 1:3 input/output agent workload, that blends to roughly $0.57 per million tokens.
What is the Gemma 4 27B context window?
Gemma 4 27B supports a 256K token context window and generates at a median 174 output tokens per second. That context fits roughly 171 standard documents in a single prompt.
Is Gemma 4 27B open source?
Yes — Gemma 4 27B ships open weights that you can download and self-host or serve through any compatible inference provider.
What is better than Gemma 4 27B?
Qwen3.8 Flash ranks one place higher at #34 with an AMR score of 74.5. Gemma 4 27B still wins 3 of the tracked dimensions head-to-head — check the comparison table to see exactly which.