Model comparison
Gemma 3 27B vs Muse Spark 1.3
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 30.8 on the Noometry Index. Gemma 3 27B costs 20× 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 3 27B scores higher in 0 categories and Muse Spark 1.3 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Spark 1.3 leads 73.1 to 25.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 22.5% for Gemma 3 27B and 99.2% for Muse Spark 1.3.
- Gemma 3 27B is cheaper at $0.08 / $0.16 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 27B has downloadable open weights; the other is API-only.
Side by side
| Gemma 3 27B | Muse Spark 1.3 | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 30.8 | 54.8 |
| Released | 2025-03-11 | 2026-09-02 |
| Weights | Open | Proprietary |
| Context window | 131K | 1.05M |
| Max output | 8K | 131K |
| Input $ / M tokens | $0.08 | $1.25 |
| Output $ / M tokens | $0.16 | $4.25 |
| Results tracked | 43 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.3 leads
Gemma 3 27B: 22.5 (#334), Muse Spark 1.3: 56.6 (#21)
| Benchmark | Gemma 3 27B | Muse Spark 1.3 |
|---|---|---|
| SciCode | 21.2% | 59.7% |
| LMArena Coding | 1322 | 1514 |
| Aider Polyglot | 4.9% | — |
| CursorBench | — | 41.6% |
| LMArena WebDev | — | 1657 |
| LiveBench Coding | 39.9% | — |
Agentic & Tool Use Muse Spark 1.3 leads
Gemma 3 27B: 25.1 (#110), Muse Spark 1.3: 38.6 (#30)
| Benchmark | Gemma 3 27B | Muse Spark 1.3 |
|---|---|---|
| APEX-Agents | — | 57.8% |
| Berkeley Function Calling Leaderboard | 29.5% | — |
| GDP.pdf | — | 27.6% |
Reasoning Muse Spark 1.3 leads
Gemma 3 27B: 16.7 (#301), Muse Spark 1.3: 54.0 (#27)
| Benchmark | Gemma 3 27B | Muse Spark 1.3 |
|---|---|---|
| CritPt | 0% | 26% |
| Chess Puzzles | 0% | 38% |
| LMArena Hard Prompts | 1340 | 1503 |
| DTBench | 52.5% | 96.5% |
| LMCA | 12.3% | 53.9% |
| Epoch Capabilities Index | 130.04 | 156.75 |
| Kagi LLM Benchmark | 40.4% | — |
| NYT Connections (extended) | — | 85.1% |
| LiveBench Reasoning | 43.8% | — |
| Mystery Game Puzzles | — | 25% |
| LiveBench Data Analysis | 51.5% | — |
| Bench to the Future 3 | — | 0.14 |
| LiveBench | 50% | — |
Math Muse Spark 1.3 leads
Gemma 3 27B: 25.9 (#265), Muse Spark 1.3: 73.1 (#21)
| Benchmark | Gemma 3 27B | Muse Spark 1.3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 22.5% | 99.2% |
| LMArena Math | 1312 | 1494 |
| FrontierMath (Tiers 1-3) | — | 74.4% |
| FrontierMath Tier 4 | — | 46.3% |
| ProofBench | — | 58% |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |
Knowledge Muse Spark 1.3 leads
Gemma 3 27B: 25.5 (#261), Muse Spark 1.3: 42.6 (#95)
| Benchmark | Gemma 3 27B | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1304 | 1516 |
| GPQA Diamond | 47.7% | — |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Muse Spark 1.3 leads
Gemma 3 27B: 32.6 (#100), Muse Spark 1.3: 43.7 (#22)
| Benchmark | Gemma 3 27B | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | 1164 | 1309 |
| GeoBench | 52% | — |
| LMArena Document | — | 1471 |
Multilingual Muse Spark 1.3 leads
Gemma 3 27B: 46.9 (#155), Muse Spark 1.3: 57.4 (#8)
| Benchmark | Gemma 3 27B | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1334 | 1481 |
| LMArena Chinese | 1346 | 1529 |
| LMArena French | 1368 | 1524 |
| LMArena German | 1362 | 1515 |
| LMArena Japanese | 1287 | 1474 |
| LMArena Korean | 1308 | 1501 |
| LMArena Russian | 1349 | 1490 |
| LMArena Spanish | 1349 | 1490 |
Instruction Following Muse Spark 1.3 leads
Gemma 3 27B: 70.6 (#160), Muse Spark 1.3: 77.5 (#22)
| Benchmark | Gemma 3 27B | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1321 | 1477 |
| LiveBench Instruction Following | 74.9% | — |
Long Context Muse Spark 1.3 leads
Gemma 3 27B: 27.6 (#293), Muse Spark 1.3: 45.6 (#32)
| Benchmark | Gemma 3 27B | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1333 | 1488 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Muse Spark 1.3 leads
Gemma 3 27B: 52.5 (#168), Muse Spark 1.3: 73.6 (#9)
| Benchmark | Gemma 3 27B | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1358 | 1490 |
| LMArena Creative Writing | 1346 | 1455 |
| EQ-Bench Creative Writing | 1266 | 1906 |
| LMArena Multi-Turn | 1345 | 1482 |
| Short-Story Creative Writing | 79.9% | — |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than Muse Spark 1.3?
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 30.8 on the Noometry Index. Gemma 3 27B costs 20× 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 27B or Muse Spark 1.3?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; Muse Spark 1.3 lists at $1.25 and $4.25.
Is Gemma 3 27B or Muse Spark 1.3 better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 22.5 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 27B and Muse Spark 1.3 share?
26 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Muse Spark 1.3 has 37.