Model comparison
Muse Spark vs Qwen1.5-32B
Muse Spark is the stronger model overall, scoring 50.6 to 30.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Muse Spark scores higher in 8 categories and Qwen1.5-32B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 13.5.
- The biggest single-benchmark swing is GPQA Diamond: 89.8% for Muse Spark and 30.7% for Qwen1.5-32B.
- Qwen1.5-32B has downloadable open weights; the other is API-only.
Side by side
| Muse Spark | Qwen1.5-32B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 50.6 | 30.5 |
| Released | 2026-04-08 | 2024-02-04 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 27 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
Muse Spark: 46.2 (#69), Qwen1.5-32B: 31.7 (#282)
| Benchmark | Muse Spark | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 1481 | 1155 |
| SciCode | 51.5% | — |
| BigCodeBench Instruct | — | 32.3% |
| BigCodeBench Complete | — | 42% |
Reasoning Muse Spark leads
Muse Spark: 35.9 (#67), Qwen1.5-32B: 21.8 (#212)
| Benchmark | Muse Spark | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1474 | 1130 |
| CritPt | 11.3% | — |
| Epoch Capabilities Index | 152.04 | — |
Math Muse Spark leads
Muse Spark: 47.8 (#66), Qwen1.5-32B: 33.0 (#207)
| Benchmark | Muse Spark | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1455 | 1155 |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 17% | — |
| FrontierMath (Feb 2025 set) | 39% | — |
| FrontierMath Tier 4 (v1) | 14.6% | — |
Knowledge Muse Spark leads
Muse Spark: 65.7 (#13), Qwen1.5-32B: 13.5 (#296)
| Benchmark | Muse Spark | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 89.8% | 30.7% |
| LMArena Expert | 1457 | 1126 |
| Humanity's Last Exam | 40.6% | — |
| MMLU | — | 74.4% |
Multimodal Not comparable
Muse Spark: 43.4 (#24), Qwen1.5-32B: —
| Benchmark | Muse Spark | Qwen1.5-32B |
|---|---|---|
| LMArena Vision | 1306 | — |
| LMArena Document | 1444 | — |
Multilingual Muse Spark leads
Muse Spark: 56.1 (#24), Qwen1.5-32B: 31.4 (#259)
| Benchmark | Muse Spark | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1464 | 1106 |
| LMArena Chinese | 1509 | 1177 |
| LMArena French | 1497 | 1101 |
| LMArena German | 1497 | 1058 |
| LMArena Korean | 1459 | 1008 |
| LMArena Russian | 1466 | 1073 |
| LMArena Spanish | 1472 | 1089 |
| LMArena Japanese | — | 1027 |
Instruction Following Muse Spark leads
Muse Spark: 75.9 (#51), Qwen1.5-32B: 57.7 (#265)
| Benchmark | Muse Spark | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1442 | 1116 |
Long Context Muse Spark leads
Muse Spark: 44.4 (#69), Qwen1.5-32B: 34.7 (#246)
| Benchmark | Muse Spark | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1451 | 1146 |
Writing & Preference Muse Spark leads
Muse Spark: 66.0 (#39), Qwen1.5-32B: 34.2 (#271)
| Benchmark | Muse Spark | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1474 | 1137 |
| LMArena Creative Writing | 1459 | 1083 |
| LMArena Multi-Turn | 1477 | 1140 |
Frequently asked questions
Is Muse Spark better than Qwen1.5-32B?
Muse Spark is the stronger model overall, scoring 50.6 to 30.5 on the Noometry Index.
Is Muse Spark or Qwen1.5-32B better for coding?
Muse Spark scores higher on coding benchmarks: 46.2 versus 31.7 in the Noometry coding category.
How many benchmarks do Muse Spark and Qwen1.5-32B share?
17 benchmarks have published results for both models. Muse Spark has 27 scored results on Noometry and Qwen1.5-32B has 21.