The AI arena is free today

Open Superagent

Gemma 4 31B vs Qwen3 Max Thinking

Gemma 4 31B and Qwen3 Max Thinking are closely matched at 33.2 and 33.0 on the LLM Stats Score. Gemma 4 31B is 15.7x cheaper per token.

Google · Alibaba Cloud / Qwen Team · Updated for 2026

Which is better?

Gemma 4 31B and Qwen3 Max Thinking are closely matched on the overall LLM Stats Score at 33.2 and 33.0.

In the 5 individual benchmarks reported for both models, Qwen3 Max Thinking wins 4; this is a narrower head-to-head signal than the composite indexes.

On price, Gemma 4 31B is roughly 15.7x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Gemma 4 31B also accepts a larger context window (262,144 input tokens), making it the stronger choice for long documents and large codebases.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Gemma 4 31B

  • cost matters — it's about 15.7x cheaper per token
  • you process long inputs — it offers a 262,144 token context window
  • you want the most recent training data — it shipped Apr 2026
  • you need open weights you can self-host or fine-tune

Choose Qwen3 Max Thinking

  • you value its reported benchmark strengths — it wins 4 of 5 exact shared results

At a glance

The differences that matter most.

Core performance indexes
33.2
#99
33.0
#101
33.7
#92
34.1
#90
13.7
#89
10.3
#115
Cost, coverage & limits
Benchmark wins
1 of 5
4 of 5
Input price
$0.09 / M
$1.20 / M
Output price
$0.34 / M
$6.00 / M
Context window
262,144
256,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

2 shared
Index
Gemma 4 31B
Qwen3 Max Thinking
29.5#83
32.2#62
16.7#45
22.6#21
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

12 reported for Gemma 4 31B · 34 for Qwen3 Max Thinking

5 shared

Gemma 4 31B outperforms in 1 benchmarks (MMMLU), while Qwen3 Max Thinking is better at 4 benchmarks (AIME 2026, GPQA, LiveCodeBench v6, MMLU-Pro).

Qwen3 Max Thinking significantly outperforms across most benchmarks.

Wed Sep 09 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Gemma 4 31B costs less

For input processing, Gemma 4 31B ($0.09/1M tokens) is 13.3x cheaper than Qwen3 Max Thinking ($1.20/1M tokens).

For output processing, Gemma 4 31B ($0.34/1M tokens) is 17.6x cheaper than Qwen3 Max Thinking ($6.00/1M tokens).

In conclusion, Qwen3 Max Thinking is more expensive than Gemma 4 31B.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Wed Sep 09 2026 • llm-stats.com
Google
Gemma 4 31B
Input tokens$0.09
Output tokens$0.34
Best providerDeepinfra
Alibaba Cloud / Qwen Team
Qwen3 Max Thinking
Input tokens$1.20
Output tokens$6.00
Best providerDeepinfra
Notice missing or incorrect data?Start an Issue

Model Size

Parameter count comparison

969.3B diff

Qwen3 Max Thinking has 969.3B more parameters than Gemma 4 31B, making it 3157.3% larger.

Google
Gemma 4 31B
30.7Bparameters
Alibaba Cloud / Qwen Team
Qwen3 Max Thinking
1.0Tparameters
30.7B
Gemma 4 31B
1000.0B
Qwen3 Max Thinking

Context Window

Maximum input and output token capacity

Gemma 4 31B accepts 262,144 input tokens compared to Qwen3 Max Thinking's 256,000 tokens. Gemma 4 31B can generate longer responses up to 262,144 tokens, while Qwen3 Max Thinking is limited to 256,000 tokens.

Google
Gemma 4 31B
Input262,144 tokens
Output262,144 tokens
Alibaba Cloud / Qwen Team
Qwen3 Max Thinking
Input256,000 tokens
Output256,000 tokens
Wed Sep 09 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Gemma 4 31B supports multimodal inputs, whereas Qwen3 Max Thinking does not.

Gemma 4 31B can handle both text and other forms of data like images, making it suitable for multimodal applications.

Gemma 4 31B

Text
Images
Audio
Video

Qwen3 Max Thinking

Text
Images
Audio
Video

License

Usage and distribution terms

Gemma 4 31B is licensed under Apache 2.0, while Qwen3 Max Thinking uses a proprietary license.

License differences may affect how you can use these models in commercial or open-source projects.

Gemma 4 31B

Apache 2.0

Open weights

Qwen3 Max Thinking

Proprietary

Closed source

Release Timeline

When each model was launched

Gemma 4 31B was released on 2026-04-02, while Qwen3 Max Thinking was released on 2026-02-13.

Gemma 4 31B is 2 months newer than Qwen3 Max Thinking.

Gemma 4 31B

Apr 2, 2026

5 months ago

1mo newer
Qwen3 Max Thinking

Feb 13, 2026

6 months ago

Knowledge Cutoff

When training data ends

Gemma 4 31B has a documented knowledge cutoff of 2025-01-01, while Qwen3 Max Thinking'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 Max Thinking's cutoff date.

Gemma 4 31B

Jan 2025

Qwen3 Max Thinking

Provider Availability

Gemma 4 31B is available from DeepInfra, FriendliAI, Novita, Together. Qwen3 Max Thinking is available from DeepInfra.

Gemma 4 31B

deepinfra logo
Deepinfra
Input Price:Input: $0.09/1MOutput Price:Output: $0.34/1M
friendli logo
FriendliAI
Input Price:Input: $0.14/1MOutput Price:Output: $0.40/1M
novita logo
Novita
Input Price:Input: $0.14/1MOutput Price:Output: $0.40/1M
together logo
Together
Input Price:Input: $0.39/1MOutput Price:Output: $0.97/1M

Qwen3 Max Thinking

deepinfra logo
Deepinfra
Input Price:Input: $1.20/1MOutput Price:Output: $6.00/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against Gemma 4 31B and Qwen3 Max Thinking side-by-side, then vote on the output you prefer.

Gemma 4 31B
✓ Preferred
Qwen3 Max Thinking
Open in Playground

FAQ

Common questions about Gemma 4 31B vs Qwen3 Max Thinking.

Which is better, Gemma 4 31B or Qwen3 Max Thinking?

Gemma 4 31B and Qwen3 Max Thinking are closely matched on the LLM Stats Score at 33.2 and 33.0. Gemma 4 31B is made by Google and Qwen3 Max Thinking is made by Alibaba Cloud / Qwen Team. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Gemma 4 31B compare to Qwen3 Max Thinking in benchmarks?

Gemma 4 31B scores AIME 2026: 89.2%, MMMLU: 88.4%, t2-bench: 86.4%, MathVision: 85.6%, MMLU-Pro: 85.2%. Qwen3 Max Thinking scores C-Eval: 93.7%, IFEval: 93.4%, AIME 2026: 93.3%, MMLU-Redux: 92.8%, GPQA: 87.4%.

Is Gemma 4 31B cheaper than Qwen3 Max Thinking?

Gemma 4 31B is 13.3x cheaper for input tokens. Gemma 4 31B costs $0.09/M input and $0.34/M output via deepinfra. Qwen3 Max Thinking costs $1.20/M input and $6.00/M output via deepinfra.

What are the context window sizes for Gemma 4 31B and Qwen3 Max Thinking?

Gemma 4 31B supports 262K tokens and Qwen3 Max Thinking supports 256K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Gemma 4 31B and Qwen3 Max Thinking?

Key differences include LLM Stats Score (33.2 vs 33.0), context window (262K vs 256K), input pricing ($0.09 vs $1.20/M), multimodal support (yes vs no), licensing (Apache 2.0 vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes Gemma 4 31B and Qwen3 Max Thinking?

Gemma 4 31B is developed by Google and Qwen3 Max Thinking is developed by Alibaba Cloud / Qwen Team.