The AI arena is free today

Open Superagent

Gemma 4 31B vs Muse Spark 1.3

Muse Spark 1.3 leads the LLM Stats Score 55.3 to 33.2. Muse Spark 1.3 is 1.5x cheaper per token.

Google · Meta · Updated for 2026

Which is better?

Muse Spark 1.3 leads the overall LLM Stats Score 55.3 to 33.2, ranking #5 overall.

In the 1 individual benchmarks reported for both models, Muse Spark 1.3 wins 1; this is a narrower head-to-head signal than the composite indexes.

On price, Muse Spark 1.3 is roughly 1.5x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Muse Spark 1.3 also accepts a larger context window (1,048,576 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

  • you need open weights you can self-host or fine-tune

Choose Muse Spark 1.3

  • overall performance matters — it scores 55.3 and ranks #5 on LLM Stats
  • your work emphasizes reasoning and agents — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 1 of 1 exact shared results
  • cost matters — it's about 1.5x cheaper per token
  • you process long inputs — it offers a 1,048,576 token context window
  • you want the most recent training data — it shipped Sep 2026

At a glance

The differences that matter most.

Core performance indexes
33.2
#94
55.3
#5
33.9
#86
52.8
#7
13.5
#86
40.4
#4
Cost, coverage & limits
Benchmark wins
0 of 1
1 of 1
Input price
$0.13 / M
$0.10 / M
Output price
$0.38 / M
$0.20 / M
Context window
262,144
1,048,576

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Gemma 4 31B
Muse Spark 1.3
17.0#42
31.7#1
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

12 reported for Gemma 4 31B · 11 for Muse Spark 1.3

1 shared

Gemma 4 31B outperforms in 0 benchmarks, while Muse Spark 1.3 is better at 1 benchmark (MRCR v2 (8-needle)).

Muse Spark 1.3 significantly outperforms across most benchmarks.

Sat Sep 05 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Muse Spark 1.3 costs less

For input processing, Gemma 4 31B ($0.13/1M tokens) is 1.3x more expensive than Muse Spark 1.3 ($0.10/1M tokens).

For output processing, Gemma 4 31B ($0.38/1M tokens) is 1.9x more expensive than Muse Spark 1.3 ($0.20/1M tokens).

In conclusion, Gemma 4 31B is more expensive than Muse Spark 1.3.*

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

Lowest available price from all providers
Sat Sep 05 2026 • llm-stats.com
Google
Gemma 4 31B
Input tokens$0.13
Output tokens$0.38
Best providerDeepinfra
Meta
Muse Spark 1.3
Input tokens$0.10
Output tokens$0.20
Best providerMeta
Notice missing or incorrect data?Start an Issue

Context Window

Maximum input and output token capacity

Muse Spark 1.3 accepts 1,048,576 input tokens compared to Gemma 4 31B's 262,144 tokens. Muse Spark 1.3 can generate longer responses up to 943,718 tokens, while Gemma 4 31B is limited to 131,072 tokens.

Google
Gemma 4 31B
Input262,144 tokens
Output131,072 tokens
Meta
Muse Spark 1.3
Input1,048,576 tokens
Output943,718 tokens
Sat Sep 05 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both Gemma 4 31B and Muse Spark 1.3 support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

Gemma 4 31B

Text
Images
Audio
Video

Muse Spark 1.3

Text
Images
Audio
Video

License

Usage and distribution terms

Gemma 4 31B is licensed under Apache 2.0, while Muse Spark 1.3 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

Muse Spark 1.3

Proprietary

Closed source

Release Timeline

When each model was launched

Gemma 4 31B was released on 2026-04-02, while Muse Spark 1.3 was released on 2026-09-02.

Muse Spark 1.3 is 5 months newer than Gemma 4 31B.

Gemma 4 31B

Apr 2, 2026

5 months ago

Muse Spark 1.3

Sep 2, 2026

3 days ago

5mo newer

Knowledge Cutoff

When training data ends

Gemma 4 31B has a documented knowledge cutoff of 2025-01-01, while Muse Spark 1.3'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 Muse Spark 1.3's cutoff date.

Gemma 4 31B

Jan 2025

Muse Spark 1.3

Provider Availability

Gemma 4 31B is available from DeepInfra, FriendliAI, Novita, Together. Muse Spark 1.3 is available from Meta Model API.

Gemma 4 31B

deepinfra logo
Deepinfra
Input Price:Input: $0.13/1MOutput Price:Output: $0.38/1M
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

Muse Spark 1.3

meta logo
Meta
Input Price:Input: $0.10/1MOutput Price:Output: $0.20/1M
* 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 Muse Spark 1.3 side-by-side, then vote on the output you prefer.

Gemma 4 31B
✓ Preferred
Muse Spark 1.3
Open in Playground

FAQ

Common questions about Gemma 4 31B vs Muse Spark 1.3.

Which is better, Gemma 4 31B or Muse Spark 1.3?

Muse Spark 1.3 leads the LLM Stats Score 55.3 to 33.2. Gemma 4 31B is made by Google and Muse Spark 1.3 is made by Meta. 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 Muse Spark 1.3 in benchmarks?

Gemma 4 31B scores AIME 2026: 89.2%, MMMLU: 88.4%, t2-bench: 86.4%, MathVision: 85.6%, MMLU-Pro: 85.2%. Muse Spark 1.3 scores MRCR v2 (8-needle): 98.5%, MRCR v2 (8-needle, 512K-1M): 98.1%, DeepSearchQA: 89.4%, Terminal-Bench 2.1: 88.8%, DeepSWE 1.1: 75.4%.

Is Gemma 4 31B cheaper than Muse Spark 1.3?

Muse Spark 1.3 is 1.3x cheaper for input tokens. Gemma 4 31B costs $0.13/M input and $0.38/M output via deepinfra. Muse Spark 1.3 costs $0.10/M input and $0.20/M output via meta.

What are the context window sizes for Gemma 4 31B and Muse Spark 1.3?

Gemma 4 31B supports 262K tokens and Muse Spark 1.3 supports 1.0M 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 Muse Spark 1.3?

Key differences include LLM Stats Score (33.2 vs 55.3), context window (262K vs 1.0M), input pricing ($0.13 vs $0.10/M), licensing (Apache 2.0 vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes Gemma 4 31B and Muse Spark 1.3?

Gemma 4 31B is developed by Google and Muse Spark 1.3 is developed by Meta.