Model comparison
Gemma 3 12B vs Muse Spark 1.3
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 32.1 on the Noometry Index. Gemma 3 12B costs 27× less per token, which makes it the better buy when Muse Spark 1.3's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Google
MetaSummary
- They share 20 benchmarks with published results for both. Gemma 3 12B 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 22.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 16.7% for Gemma 3 12B and 99.2% for Muse Spark 1.3.
- Gemma 3 12B is cheaper at $0.05 / $0.15 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 12B has downloadable open weights; the other is API-only.
Side by side
| Gemma 3 12B | Muse Spark 1.3 | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 32.1 | 54.8 |
| Released | 2025-03-12 | 2026-09-02 |
| Weights | Open | Proprietary |
| Context window | 131K | 1.05M |
| Max output | 8K | 131K |
| Input $ / M tokens | $0.05 | $1.25 |
| Output $ / M tokens | $0.15 | $4.25 |
| Results tracked | 24 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.3 leads
Gemma 3 12B: 31.7 (#280), Muse Spark 1.3: 56.6 (#21)
| Benchmark | Gemma 3 12B | Muse Spark 1.3 |
|---|---|---|
| SciCode | 17.4% | 59.7% |
| LMArena Coding | 1281 | 1514 |
| CursorBench | — | 41.6% |
| LMArena WebDev | — | 1657 |
Agentic & Tool Use Muse Spark 1.3 leads
Gemma 3 12B: 25.5 (#108), Muse Spark 1.3: 38.6 (#30)
| Benchmark | Gemma 3 12B | Muse Spark 1.3 |
|---|---|---|
| APEX-Agents | — | 57.8% |
| Berkeley Function Calling Leaderboard | 30.4% | — |
| GDP.pdf | — | 27.6% |
Reasoning Muse Spark 1.3 leads
Gemma 3 12B: 15.7 (#313), Muse Spark 1.3: 54.0 (#27)
| Benchmark | Gemma 3 12B | Muse Spark 1.3 |
|---|---|---|
| CritPt | 0% | 26% |
| Chess Puzzles | 0% | 38% |
| LMArena Hard Prompts | 1309 | 1503 |
| DTBench | 48.8% | 96.5% |
| LMCA | 4.5% | 53.9% |
| Epoch Capabilities Index | 123.5 | 156.75 |
| NYT Connections (extended) | — | 85.1% |
| Mystery Game Puzzles | — | 25% |
| Bench to the Future 3 | — | 0.14 |
Math Muse Spark 1.3 leads
Gemma 3 12B: 22.3 (#279), Muse Spark 1.3: 73.1 (#21)
| Benchmark | Gemma 3 12B | Muse Spark 1.3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.7% | 99.2% |
| LMArena Math | 1307 | 1494 |
| FrontierMath (Tiers 1-3) | — | 74.4% |
| FrontierMath Tier 4 | — | 46.3% |
| ProofBench | — | 58% |
Knowledge Muse Spark 1.3 leads
Gemma 3 12B: 26.5 (#257), Muse Spark 1.3: 42.6 (#95)
| Benchmark | Gemma 3 12B | Muse Spark 1.3 |
|---|---|---|
| LMArena Expert | 1248 | 1516 |
| GPQA Diamond | 39.5% | — |
| Vectara Hallucination Rate | 4.4% | — |
Multimodal Not comparable
Gemma 3 12B: —, Muse Spark 1.3: 43.7 (#22)
| Benchmark | Gemma 3 12B | Muse Spark 1.3 |
|---|---|---|
| LMArena Vision | — | 1309 |
| LMArena Document | — | 1471 |
| MindCube | 46.7% | — |
Multilingual Muse Spark 1.3 leads
Gemma 3 12B: 45.7 (#165), Muse Spark 1.3: 57.4 (#8)
| Benchmark | Gemma 3 12B | Muse Spark 1.3 |
|---|---|---|
| LMArena Non-English | 1318 | 1481 |
| LMArena German | 1370 | 1515 |
| LMArena Russian | 1335 | 1490 |
| LMArena Chinese | — | 1529 |
| LMArena French | — | 1524 |
| LMArena Japanese | — | 1474 |
| LMArena Korean | — | 1501 |
| LMArena Spanish | — | 1490 |
Instruction Following Muse Spark 1.3 leads
Gemma 3 12B: 68.6 (#186), Muse Spark 1.3: 77.5 (#22)
| Benchmark | Gemma 3 12B | Muse Spark 1.3 |
|---|---|---|
| LMArena Instruction Following | 1299 | 1477 |
Long Context Muse Spark 1.3 leads
Gemma 3 12B: 40.0 (#162), Muse Spark 1.3: 45.6 (#32)
| Benchmark | Gemma 3 12B | Muse Spark 1.3 |
|---|---|---|
| LMArena Longer Query | 1317 | 1488 |
Writing & Preference Muse Spark 1.3 leads
Gemma 3 12B: 47.5 (#209), Muse Spark 1.3: 73.6 (#9)
| Benchmark | Gemma 3 12B | Muse Spark 1.3 |
|---|---|---|
| LMArena Text | 1334 | 1490 |
| LMArena Creative Writing | 1331 | 1455 |
| EQ-Bench Creative Writing | 1126 | 1906 |
| LMArena Multi-Turn | 1334 | 1482 |
Frequently asked questions
Is Gemma 3 12B better than Muse Spark 1.3?
Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 32.1 on the Noometry Index. Gemma 3 12B costs 27× 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 12B or Muse Spark 1.3?
Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; Muse Spark 1.3 lists at $1.25 and $4.25.
Is Gemma 3 12B or Muse Spark 1.3 better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 31.7 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 12B and Muse Spark 1.3 share?
20 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Muse Spark 1.3 has 37.