Model comparison
Gemma 2 9B vs Muse Spark
Muse Spark is the stronger model overall, scoring 50.3 to 25.7 on the Noometry Index.
Last verified . 19 shared benchmarks.
Summary
- They share 19 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and Muse Spark in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 9.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.6% for Gemma 2 9B and 88.9% for Muse Spark.
- Gemma 2 9B has downloadable open weights; the other is API-only.
Side by side
| Gemma 2 9B | Muse Spark | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 25.7 | 50.3 |
| Released | 2024-06-24 | 2026-04-08 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
Gemma 2 9B: 29.0 (#299), Muse Spark: 45.6 (#65)
| Benchmark | Gemma 2 9B | Muse Spark |
|---|---|---|
| LMArena Coding | 1174 | 1482 |
| SciCode | — | 51.5% |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |
Reasoning Muse Spark leads
Gemma 2 9B: 15.3 (#306), Muse Spark: 34.9 (#61)
| Benchmark | Gemma 2 9B | Muse Spark |
|---|---|---|
| LMArena Hard Prompts | 1172 | 1475 |
| Epoch Capabilities Index | 119.78 | 152.09 |
| CritPt | — | 11.3% |
| LiveBench Reasoning | 15.2% | — |
| LiveBench Data Analysis | 36.4% | — |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |
Math Muse Spark leads
Gemma 2 9B: 9.3 (#312), Muse Spark: 46.8 (#57)
| Benchmark | Gemma 2 9B | Muse Spark |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 88.9% |
| LMArena Math | 1183 | 1455 |
| ProofBench | — | 17% |
| LiveBench Math | 19.8% | — |
| MATH Level 5 | 21% | — |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |
| GSM8K | 84.9% | — |
Knowledge Muse Spark leads
Gemma 2 9B: 9.7 (#300), Muse Spark: 65.7 (#12)
| Benchmark | Gemma 2 9B | Muse Spark |
|---|---|---|
| GPQA Diamond | 27.5% | 89.8% |
| LMArena Expert | 1147 | 1458 |
| Humanity's Last Exam | — | 40.6% |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |
Multimodal Not comparable
Gemma 2 9B: —, Muse Spark: 42.7 (#23)
| Benchmark | Gemma 2 9B | Muse Spark |
|---|---|---|
| LMArena Vision | — | 1306 |
| LMArena Document | — | 1444 |
Multilingual Muse Spark leads
Gemma 2 9B: 36.8 (#233), Muse Spark: 56.3 (#23)
| Benchmark | Gemma 2 9B | Muse Spark |
|---|---|---|
| LMArena Non-English | 1188 | 1464 |
| LMArena Chinese | 1185 | 1507 |
| LMArena French | 1189 | 1497 |
| LMArena German | 1186 | 1497 |
| LMArena Korean | 1137 | 1457 |
| LMArena Russian | 1200 | 1467 |
| LMArena Spanish | 1200 | 1471 |
| LMArena Japanese | 1144 | — |
Instruction Following Muse Spark leads
Gemma 2 9B: 57.8 (#264), Muse Spark: 76.1 (#47)
| Benchmark | Gemma 2 9B | Muse Spark |
|---|---|---|
| LMArena Instruction Following | 1178 | 1443 |
| LiveBench Instruction Following | 52.6% | — |
Long Context Muse Spark leads
Gemma 2 9B: 36.3 (#228), Muse Spark: 44.4 (#65)
| Benchmark | Gemma 2 9B | Muse Spark |
|---|---|---|
| LMArena Longer Query | 1197 | 1451 |
Writing & Preference Muse Spark leads
Gemma 2 9B: 32.3 (#276), Muse Spark: 66.2 (#37)
| Benchmark | Gemma 2 9B | Muse Spark |
|---|---|---|
| LMArena Text | 1207 | 1474 |
| LMArena Creative Writing | 1206 | 1460 |
| LMArena Multi-Turn | 1193 | 1477 |
| EQ-Bench Creative Writing | 841 | — |
| LiveBench Language | 25.5% | — |
Frequently asked questions
Is Gemma 2 9B better than Muse Spark?
Muse Spark is the stronger model overall, scoring 50.3 to 25.7 on the Noometry Index.
Is Gemma 2 9B or Muse Spark better for coding?
Muse Spark scores higher on coding benchmarks: 45.6 versus 29.0 in the Noometry coding category.
How many benchmarks do Gemma 2 9B and Muse Spark share?
19 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Muse Spark has 27.