Model comparison
Muse Spark 1.3 vs Qwen3.5-9B
Muse Spark 1.3 is the stronger model overall, scoring 54.4 to 33.3 on the Noometry Index. Qwen3.5-9B costs 18× less per token, which makes it the better buy when Muse Spark 1.3's lead doesn't matter for your workload.
Last verified . 7 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 7 benchmarks with published results for both. Muse Spark 1.3 scores higher in 4 categories and Qwen3.5-9B in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Muse Spark 1.3 leads 72.4 to 33.5.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 99.2% for Muse Spark 1.3 and 61.7% for Qwen3.5-9B.
- Qwen3.5-9B is cheaper at $0.10 / $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 262K.
- Qwen3.5-9B has downloadable open weights; the other is API-only.
Side by side
| Muse Spark 1.3 | Qwen3.5-9B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 54.4 | 33.3 |
| Released | 2026-09-02 | 2026-02-23 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 131K | 66K |
| Input $ / M tokens | $1.25 | $0.10 |
| Output $ / M tokens | $4.25 | $0.15 |
| Results tracked | 34 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.3 leads
Muse Spark 1.3: 56.1 (#18), Qwen3.5-9B: 35.3 (#213)
| Benchmark | Muse Spark 1.3 | Qwen3.5-9B |
|---|---|---|
| SciCode | 59.7% | 27.5% |
| CursorBench | 41.6% | — |
| LMArena WebDev | 1655 | — |
| LMArena Coding | 1516 | — |
Agentic & Tool Use Muse Spark 1.3 leads
Muse Spark 1.3: 38.6 (#28), Qwen3.5-9B: 14.4 (#143)
| Benchmark | Muse Spark 1.3 | Qwen3.5-9B |
|---|---|---|
| Terminal-Bench | — | 9.2% |
| APEX-Agents | 57.8% | — |
| GDP.pdf | 27.6% | — |
Reasoning Muse Spark 1.3 leads
Muse Spark 1.3: 52.9 (#27), Qwen3.5-9B: 22.5 (#178)
| Benchmark | Muse Spark 1.3 | Qwen3.5-9B |
|---|---|---|
| CritPt | 24.9% | 0.3% |
| Chess Puzzles | 38% | 12% |
| DTBench | 96.5% | 71.2% |
| LMCA | 53.9% | 24.5% |
| Epoch Capabilities Index | 156.89 | 139.45 |
| NYT Connections (extended) | 85.1% | — |
| LMArena Hard Prompts | 1503 | — |
| Mystery Game Puzzles | 25% | — |
| Bench to the Future 3 | 0.14 | — |
Math Muse Spark 1.3 leads
Muse Spark 1.3: 72.4 (#16), Qwen3.5-9B: 33.5 (#174)
| Benchmark | Muse Spark 1.3 | Qwen3.5-9B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 99.2% | 61.7% |
| FrontierMath (Tiers 1-3) | 74.4% | — |
| FrontierMath Tier 4 | 46.3% | — |
| MathArena Final-Answer Competitions | — | 48.5% |
| LMArena Math | 1497 | — |
Knowledge Qwen3.5-9B leads
Muse Spark 1.3: 42.0 (#92), Qwen3.5-9B: 46.0 (#77)
| Benchmark | Muse Spark 1.3 | Qwen3.5-9B |
|---|---|---|
| GPQA Diamond | — | 79% |
| LMArena Expert | 1516 | — |
Multimodal Not comparable
Muse Spark 1.3: 43.0 (#21), Qwen3.5-9B: —
| Benchmark | Muse Spark 1.3 | Qwen3.5-9B |
|---|---|---|
| LMArena Vision | 1310 | — |
| LMArena Document | 1471 | — |
Multilingual Not comparable
Muse Spark 1.3: 57.8 (#6), Qwen3.5-9B: —
| Benchmark | Muse Spark 1.3 | Qwen3.5-9B |
|---|---|---|
| LMArena Non-English | 1485 | — |
| LMArena Chinese | 1527 | — |
| LMArena French | 1534 | — |
| LMArena Korean | 1513 | — |
| LMArena Russian | 1491 | — |
| LMArena Spanish | 1485 | — |
Instruction Following Not comparable
Muse Spark 1.3: 77.8 (#14), Qwen3.5-9B: —
| Benchmark | Muse Spark 1.3 | Qwen3.5-9B |
|---|---|---|
| LMArena Instruction Following | 1481 | — |
Long Context Not comparable
Muse Spark 1.3: 45.7 (#29), Qwen3.5-9B: —
| Benchmark | Muse Spark 1.3 | Qwen3.5-9B |
|---|---|---|
| LMArena Longer Query | 1491 | — |
Writing & Preference Not comparable
Muse Spark 1.3: 73.7 (#10), Qwen3.5-9B: —
| Benchmark | Muse Spark 1.3 | Qwen3.5-9B |
|---|---|---|
| LMArena Text | 1490 | — |
| LMArena Creative Writing | 1450 | — |
| EQ-Bench Creative Writing | 1906 | — |
| LMArena Multi-Turn | 1486 | — |
Frequently asked questions
Is Muse Spark 1.3 better than Qwen3.5-9B?
Muse Spark 1.3 is the stronger model overall, scoring 54.4 to 33.3 on the Noometry Index. Qwen3.5-9B costs 18× 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, Muse Spark 1.3 or Qwen3.5-9B?
Qwen3.5-9B is cheaper. It lists at $0.10 per million input tokens and $0.15 per million output tokens; Muse Spark 1.3 lists at $1.25 and $4.25.
Is Muse Spark 1.3 or Qwen3.5-9B better for coding?
Muse Spark 1.3 scores higher on coding benchmarks: 56.1 versus 35.3 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 Muse Spark 1.3 and Qwen3.5-9B share?
7 benchmarks have published results for both models. Muse Spark 1.3 has 34 scored results on Noometry and Qwen3.5-9B has 10.