# Gemma 3 4B vs Muse Spark 1.3

> Muse Spark 1.3 is the stronger model overall, scoring 54.4 to 27.9 on the Noometry Index. Gemma 3 4B costs 40× less per token, which makes it the better buy when Muse Spark 1.3's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemma-3-4b-vs-muse-spark-1-3
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and Muse Spark 1.3 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Spark 1.3 leads 72.4 to 15.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 7.5% for Gemma 3 4B and 99.2% for Muse Spark 1.3.
- Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.3.
- Muse Spark 1.3 accepts more context: 1.05M tokens versus 131K.
- Gemma 3 4B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemma 3 4B | Muse Spark 1.3 |
|---|---|---|
| Provider | Google | Meta |
| Noometry Index | 27.9 | 54.4 |
| Rank | 320 | 27 |
| Context | 131K | 1.05M |
| Input $/M | $0.04 | $1.25 |
| Output $/M | $0.08 | $4.25 |
| Weights | Open | Proprietary |

## Coding

- Gemma 3 4B: 35.3 (#214)
- Muse Spark 1.3: 56.1 (#18)

| Benchmark | Gemma 3 4B | Muse Spark 1.3 |
|---|---|---|
| LMArena Coding | 1230 | 1516 |
| CursorBench | — | 41.6% |
| LMArena WebDev | — | 1655 |
| SciCode | — | 59.7% |

## Agentic & Tool Use

- Gemma 3 4B: 20.7 (#134)
- Muse Spark 1.3: 38.6 (#28)

| Benchmark | Gemma 3 4B | Muse Spark 1.3 |
|---|---|---|
| APEX-Agents | — | 57.8% |
| Berkeley Function Calling Leaderboard | 19.6% | — |
| GDP.pdf | — | 27.6% |

## Reasoning

- Gemma 3 4B: 12.7 (#330)
- Muse Spark 1.3: 52.9 (#27)

| Benchmark | Gemma 3 4B | Muse Spark 1.3 |
|---|---|---|
| Chess Puzzles | 0% | 38% |
| LMArena Hard Prompts | 1253 | 1503 |
| DTBench | 50.9% | 96.5% |
| LMCA | 2.8% | 53.9% |
| Epoch Capabilities Index | 116.02 | 156.89 |
| Kagi LLM Benchmark | 25.2% | — |
| NYT Connections (extended) | — | 85.1% |
| CritPt | — | 24.9% |
| Mystery Game Puzzles | — | 25% |
| Bench to the Future 3 | — | 0.14 |

## Math

- Gemma 3 4B: 15.8 (#286)
- Muse Spark 1.3: 72.4 (#16)

| Benchmark | Gemma 3 4B | Muse Spark 1.3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.5% | 99.2% |
| LMArena Math | 1239 | 1497 |
| FrontierMath (Tiers 1-3) | — | 74.4% |
| FrontierMath Tier 4 | — | 46.3% |

## Knowledge

- Gemma 3 4B: 11.8 (#294)
- Muse Spark 1.3: 42.0 (#92)

| Benchmark | Gemma 3 4B | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1223 | 1516 |
| GPQA Diamond | 23.2% | — |
| Vectara Hallucination Rate | 6.4% | — |

## Multimodal

- Gemma 3 4B: —
- Muse Spark 1.3: 43.0 (#21)

| Benchmark | Gemma 3 4B | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | — | 1310 |
| LMArena Document | — | 1471 |

## Multilingual

- Gemma 3 4B: 42.7 (#189)
- Muse Spark 1.3: 57.8 (#6)

| Benchmark | Gemma 3 4B | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1273 | 1485 |
| LMArena Russian | 1294 | 1491 |
| LMArena Chinese | — | 1527 |
| LMArena French | — | 1534 |
| LMArena German | 1281 | — |
| LMArena Korean | — | 1513 |
| LMArena Spanish | — | 1485 |

## Instruction Following

- Gemma 3 4B: 65.4 (#219)
- Muse Spark 1.3: 77.8 (#14)

| Benchmark | Gemma 3 4B | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1239 | 1481 |

## Long Context

- Gemma 3 4B: 38.6 (#189)
- Muse Spark 1.3: 45.7 (#29)

| Benchmark | Gemma 3 4B | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1274 | 1491 |

## Writing & Preference

- Gemma 3 4B: 42.2 (#234)
- Muse Spark 1.3: 73.7 (#10)

| Benchmark | Gemma 3 4B | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1291 | 1490 |
| LMArena Creative Writing | 1270 | 1450 |
| EQ-Bench Creative Writing | 1068 | 1906 |
| LMArena Multi-Turn | 1255 | 1486 |

## FAQ

### Is Gemma 3 4B better than Muse Spark 1.3?

Muse Spark 1.3 is the stronger model overall, scoring 54.4 to 27.9 on the Noometry Index. Gemma 3 4B costs 40× less per token, which makes it the better buy when Muse Spark 1.3's lead doesn't matter for your workload.

### Which is cheaper, Gemma 3 4B or Muse Spark 1.3?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Muse Spark 1.3 lists at $1.25 and $4.25.

### Is Gemma 3 4B or Muse Spark 1.3 better for coding?

Muse Spark 1.3 scores higher on coding benchmarks: 56.1 versus 35.3 in the Noometry coding category.

### Which has the bigger context window?

Muse Spark 1.3 does, with 1.05M tokens against 131K.

### How many benchmarks do Gemma 3 4B and Muse Spark 1.3 share?

17 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Muse Spark 1.3 has 34.