# Gemma 4 31B IT vs Muse Spark 1.2

> Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 43.5 on the Noometry Index. Gemma 4 31B IT costs 13× less per token, which makes it the better buy when Muse Spark 1.2's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemma-4-31b-it-vs-muse-spark-1-2
- Last updated: 2026-10-12
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. Gemma 4 31B IT scores higher in 0 categories and Muse Spark 1.2 in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.2 leads 51.3 to 27.2.
- The biggest single-benchmark swing is SimpleQA Verified: 10.4% for Gemma 4 31B IT and 60.3% for Muse Spark 1.2.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.2.
- Muse Spark 1.2 accepts more context: 1.05M tokens versus 262K.
- Gemma 4 31B IT has downloadable open weights; the other is API-only.

## Snapshot

| | Gemma 4 31B IT | Muse Spark 1.2 |
|---|---|---|
| Provider | Google | Meta |
| Noometry Index | 43.5 | 50.3 |
| Rank | 90 | 48 |
| Context | 262K | 1.05M |
| Input $/M | $0.09 | $1.25 |
| Output $/M | $0.34 | $4.25 |
| Weights | Open | Proprietary |

## Coding

- Gemma 4 31B IT: 42.3 (#108)
- Muse Spark 1.2: 49.2 (#51)

| Benchmark | Gemma 4 31B IT | Muse Spark 1.2 |
|---|---|---|
| LMArena WebDev | 1366 | 1533 |
| SciCode | 43.4% | 56.4% |
| WeirdML | 52.3% | 60.3% |
| LMArena Coding | 1459 | 1495 |
| DeepSWE | — | 54.9% |
| FrontierSWE | — | 12% |
| ALE-Bench | 925.5 | — |

## Agentic & Tool Use

- Gemma 4 31B IT: —
- Muse Spark 1.2: 29.4 (#87)

| Benchmark | Gemma 4 31B IT | Muse Spark 1.2 |
|---|---|---|
| APEX-Agents | — | 36.4% |
| GDP.pdf | — | 16% |

## Reasoning

- Gemma 4 31B IT: 27.2 (#122)
- Muse Spark 1.2: 51.3 (#34)

| Benchmark | Gemma 4 31B IT | Muse Spark 1.2 |
|---|---|---|
| NYT Connections (extended) | 70.6% | 79.2% |
| CritPt | 1.4% | 17.7% |
| LMArena Hard Prompts | 1448 | 1486 |
| DTBench | 82.7% | 94.7% |
| LMCA | 39.3% | 48.4% |
| Epoch Capabilities Index | 142.74 | 154.87 |
| SimpleBench | — | 74.5% |
| Kagi LLM Benchmark | 63.5% | — |
| Chess Puzzles | 5% | — |
| Thematic Generalization | 53% | — |
| Surface Evolver Bench | 30.6% | — |

## Math

- Gemma 4 31B IT: 43.2 (#81)
- Muse Spark 1.2: 46.4 (#70)

| Benchmark | Gemma 4 31B IT | Muse Spark 1.2 |
|---|---|---|
| LMArena Math | 1465 | 1471 |
| OTIS Mock AIME 2024-2025 | 73.3% | — |
| ProofBench | — | 43% |

## Knowledge

- Gemma 4 31B IT: 37.9 (#151)
- Muse Spark 1.2: 54.1 (#53)

| Benchmark | Gemma 4 31B IT | Muse Spark 1.2 |
|---|---|---|
| SimpleQA Verified | 10.4% | 60.3% |
| LMArena Expert | 1465 | 1480 |
| GPQA Diamond | 75.8% | — |
| Vectara Hallucination Rate | 7.4% | — |

## Multimodal

- Gemma 4 31B IT: 41.6 (#34)
- Muse Spark 1.2: 43.4 (#25)

| Benchmark | Gemma 4 31B IT | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | 1277 | 1305 |
| LMArena Document | 1425 | — |

## Multilingual

- Gemma 4 31B IT: 53.8 (#57)
- Muse Spark 1.2: 57.1 (#11)

| Benchmark | Gemma 4 31B IT | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1431 | 1478 |
| LMArena Chinese | 1476 | 1511 |
| LMArena French | 1435 | 1513 |
| LMArena Russian | 1460 | 1487 |
| LMArena Spanish | 1444 | 1498 |

## Instruction Following

- Gemma 4 31B IT: 75.5 (#61)
- Muse Spark 1.2: 76.7 (#36)

| Benchmark | Gemma 4 31B IT | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1433 | 1461 |

## Long Context

- Gemma 4 31B IT: 44.2 (#71)
- Muse Spark 1.2: 45.2 (#48)

| Benchmark | Gemma 4 31B IT | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1446 | 1475 |

## Writing & Preference

- Gemma 4 31B IT: 60.5 (#96)
- Muse Spark 1.2: 72.3 (#14)

| Benchmark | Gemma 4 31B IT | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1443 | 1482 |
| LMArena Creative Writing | 1415 | 1449 |
| EQ-Bench Creative Writing | 1368 | 1840 |
| LMArena Multi-Turn | 1452 | 1494 |
| EQ-Bench 4 | 1120 | — |

## FAQ

### Is Gemma 4 31B IT better than Muse Spark 1.2?

Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 43.5 on the Noometry Index. Gemma 4 31B IT costs 13× less per token, which makes it the better buy when Muse Spark 1.2's lead doesn't matter for your workload.

### Which is cheaper, Gemma 4 31B IT or Muse Spark 1.2?

Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Muse Spark 1.2 lists at $1.25 and $4.25.

### Is Gemma 4 31B IT or Muse Spark 1.2 better for coding?

Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 42.3 in the Noometry coding category.

### Which has the bigger context window?

Muse Spark 1.2 does, with 1.05M tokens against 262K.

### How many benchmarks do Gemma 4 31B IT and Muse Spark 1.2 share?

25 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Muse Spark 1.2 has 31.