Gemma 4 31B vs Qwen3.5-397B-A17B
Qwen3.5-397B-A17B leads the LLM Stats Score 38.7 to 33.1. Gemma 4 31B is 7.1x cheaper per token.
Google · Alibaba Cloud / Qwen Team · Updated for 2026
Which is better?
Qwen3.5-397B-A17B leads the overall LLM Stats Score 38.7 to 33.1, ranking #66 overall.
In the 7 individual benchmarks reported for both models, Qwen3.5-397B-A17B wins 7; this is a narrower head-to-head signal than the composite indexes.
On price, Gemma 4 31B is roughly 7.1x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.
Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.
Choose Gemma 4 31B
- cost matters — it's about 7.1x cheaper per token
- you want the most recent training data — it shipped Apr 2026
Choose Qwen3.5-397B-A17B
- overall performance matters — it scores 38.7 and ranks #66 on LLM Stats
- you value its reported benchmark strengths — it wins 7 of 7 exact shared results
At a glance
The differences that matter most.
Capability indexes
Additional strengths measured across groups of related public benchmarks
Individual benchmarks
12 reported for Gemma 4 31B · 38 for Qwen3.5-397B-A17B
Gemma 4 31B outperforms in 0 benchmarks, while Qwen3.5-397B-A17B is better at 7 benchmarks (AIME 2026, GPQA, Humanity's Last Exam, LiveCodeBench v6, MMLU-Pro, MMMLU, t2-bench).
Qwen3.5-397B-A17B significantly outperforms across most benchmarks.
Human preference
Blind head-to-head votes and playground preference scores
Pricing Analysis
Price comparison per million tokens
For input processing, Gemma 4 31B ($0.09/1M tokens) is 5.0x cheaper than Qwen3.5-397B-A17B ($0.45/1M tokens).
For output processing, Gemma 4 31B ($0.34/1M tokens) is 8.8x cheaper than Qwen3.5-397B-A17B ($3.00/1M tokens).
In conclusion, Qwen3.5-397B-A17B is more expensive than Gemma 4 31B.*
* Using a 3:1 ratio of input to output tokens
Model Size
Parameter count comparison
Qwen3.5-397B-A17B has 366.3B more parameters than Gemma 4 31B, making it 1193.2% larger.
Context Window
Maximum input and output token capacity
Both models have the same input context window of 262,144 tokens. Both models can generate responses up to 262,144 tokens.
Input capabilities
Documented input modalities across available providers
Both Gemma 4 31B and Qwen3.5-397B-A17B support multimodal inputs.
They are both capable of processing various types of data, offering versatility in application.
Gemma 4 31B
Qwen3.5-397B-A17B
License
Usage and distribution terms
Both models are licensed under Apache 2.0.
Both models share the same licensing terms, providing consistent usage rights.
Apache 2.0
Open weights
Apache 2.0
Open weights
Release Timeline
When each model was launched
Gemma 4 31B was released on 2026-04-02, while Qwen3.5-397B-A17B was released on 2026-02-16.
Gemma 4 31B is 2 months newer than Qwen3.5-397B-A17B.
Apr 2, 2026
5 months ago
1mo newerFeb 16, 2026
7 months ago
Knowledge Cutoff
When training data ends
Gemma 4 31B has a documented knowledge cutoff of 2025-01-01, while Qwen3.5-397B-A17B's cutoff date is not specified.
We can confirm Gemma 4 31B's training data extends to 2025-01-01, but cannot make a direct comparison without Qwen3.5-397B-A17B's cutoff date.
Jan 2025
—
Provider Availability
Gemma 4 31B is available from DeepInfra, FriendliAI, Novita, Together. Qwen3.5-397B-A17B is available from DeepInfra, Novita.
Gemma 4 31B
Qwen3.5-397B-A17B
Outputs Comparison
Judge for yourself.
Run your own prompts against Gemma 4 31B and Qwen3.5-397B-A17B side-by-side, then vote on the output you prefer.
FAQ
Common questions about Gemma 4 31B vs Qwen3.5-397B-A17B.