Model comparison
Gemma 4 31B IT vs Muse Spark 1.3
Muse Spark 1.3 is the stronger model overall, scoring 54.8 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 1.3's lead doesn't matter for your workload.
Last verified . 26 shared benchmarks.
Google
MetaSummary
- They share 26 benchmarks with published results for both. Gemma 4 31B IT 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 73.1 to 43.2.
- The biggest single-benchmark swing is Chess Puzzles: 5% for Gemma 4 31B IT and 38% for Muse Spark 1.3.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.3.
- Muse Spark 1.3 accepts more context: 1.05M tokens versus 262K.
- Gemma 4 31B IT has downloadable open weights; the other is API-only.
Side by side
| Gemma 4 31B IT | Muse Spark 1.3 | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 43.5 | 54.8 |
| Released | 2026-04-02 | 2026-09-02 |
| Weights | Open | Proprietary |
| Context window | 262K | 1.05M |
| Max output | 33K | 131K |
| Input $ / M tokens | $0.09 | $1.25 |
| Output $ / M tokens | $0.34 | $4.25 |
| Results tracked | 35 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.3 leads
Gemma 4 31B IT: 42.3 (#108), Muse Spark 1.3: 56.6 (#21)
| Benchmark | Gemma 4 31B IT | Muse Spark 1.3 |
|---|---|---|
| LMArena WebDev | 1366 | 1657 |
| SciCode | 43.4% | 59.7% |
| LMArena Coding | 1459 | 1514 |
| CursorBench | — | 41.6% |
| WeirdML | 52.3% | — |
| ALE-Bench | 925.5 | — |
Agentic & Tool Use Not comparable
Gemma 4 31B IT: —, Muse Spark 1.3: 38.6 (#30)
| Benchmark | Gemma 4 31B IT | Muse Spark 1.3 |
|---|---|---|
| APEX-Agents | — | 57.8% |
| GDP.pdf | — | 27.6% |
Reasoning Muse Spark 1.3 leads
Gemma 4 31B IT: 27.2 (#122), Muse Spark 1.3: 54.0 (#27)
| Benchmark | Gemma 4 31B IT | Muse Spark 1.3 |
|---|---|---|
| NYT Connections (extended) | 70.6% | 85.1% |
| CritPt | 1.4% | 26% |
| Chess Puzzles | 5% | 38% |
| LMArena Hard Prompts | 1448 | 1503 |
| DTBench | 82.7% | 96.5% |
| LMCA | 39.3% | 53.9% |
| Epoch Capabilities Index | 142.74 | 156.75 |
| Kagi LLM Benchmark | 63.5% | — |
| Thematic Generalization | 53% | — |
| Mystery Game Puzzles | — | 25% |
| Surface Evolver Bench | 30.6% | — |
| Bench to the Future 3 | — | 0.14 |
Math Muse Spark 1.3 leads
Gemma 4 31B IT: 43.2 (#81), Muse Spark 1.3: 73.1 (#21)
| Benchmark | Gemma 4 31B IT | Muse Spark 1.3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | 99.2% |
| LMArena Math | 1465 | 1494 |
| FrontierMath (Tiers 1-3) | — | 74.4% |
| FrontierMath Tier 4 | — | 46.3% |
| ProofBench | — | 58% |
Knowledge Muse Spark 1.3 leads
Gemma 4 31B IT: 37.9 (#151), Muse Spark 1.3: 42.6 (#95)
| Benchmark | Gemma 4 31B IT | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1465 | 1516 |
| GPQA Diamond | 75.8% | — |
| SimpleQA Verified | 10.4% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Muse Spark 1.3 leads
Gemma 4 31B IT: 41.6 (#34), Muse Spark 1.3: 43.7 (#22)
| Benchmark | Gemma 4 31B IT | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | 1277 | 1309 |
| LMArena Document | 1425 | 1471 |
Multilingual Muse Spark 1.3 leads
Gemma 4 31B IT: 53.8 (#57), Muse Spark 1.3: 57.4 (#8)
| Benchmark | Gemma 4 31B IT | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1431 | 1481 |
| LMArena Chinese | 1476 | 1529 |
| LMArena French | 1435 | 1524 |
| LMArena Russian | 1460 | 1490 |
| LMArena Spanish | 1444 | 1490 |
| LMArena German | — | 1515 |
| LMArena Japanese | — | 1474 |
| LMArena Korean | — | 1501 |
Instruction Following Muse Spark 1.3 leads
Gemma 4 31B IT: 75.5 (#61), Muse Spark 1.3: 77.5 (#22)
| Benchmark | Gemma 4 31B IT | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1433 | 1477 |
Long Context Muse Spark 1.3 leads
Gemma 4 31B IT: 44.2 (#71), Muse Spark 1.3: 45.6 (#32)
| Benchmark | Gemma 4 31B IT | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1446 | 1488 |
Writing & Preference Muse Spark 1.3 leads
Gemma 4 31B IT: 60.5 (#96), Muse Spark 1.3: 73.6 (#9)
| Benchmark | Gemma 4 31B IT | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1443 | 1490 |
| LMArena Creative Writing | 1415 | 1455 |
| EQ-Bench Creative Writing | 1368 | 1906 |
| LMArena Multi-Turn | 1452 | 1482 |
| EQ-Bench 4 | 1120 | — |
Frequently asked questions
Is Gemma 4 31B IT better than Muse Spark 1.3?
Muse Spark 1.3 is the stronger model overall, scoring 54.8 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 1.3's lead doesn't matter for your workload.
Which is cheaper, Gemma 4 31B IT or Muse Spark 1.3?
Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; Muse Spark 1.3 lists at $1.25 and $4.25.
Is Gemma 4 31B IT or Muse Spark 1.3 better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 42.3 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.3 does, with 1.05M tokens against 262K.
How many benchmarks do Gemma 4 31B IT and Muse Spark 1.3 share?
26 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and Muse Spark 1.3 has 37.