Model comparison
Muse Spark vs Qwen3.5 397B-A17B
Muse Spark is the stronger model overall, scoring 50.3 to 45.7 on the Noometry Index.
Last verified . 20 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Muse Spark scores higher in 9 categories and Qwen3.5 397B-A17B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 53.3.
- Qwen3.5 397B-A17B has downloadable open weights; the other is API-only.
Side by side
| Muse Spark | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 50.3 | 45.7 |
| Released | 2026-04-08 | 2026-02-01 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.60 |
| Output $ / M tokens | — | $3.60 |
| Results tracked | 27 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
Muse Spark: 45.6 (#65), Qwen3.5 397B-A17B: 41.7 (#108)
| Benchmark | Muse Spark | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Coding | 1482 | 1464 |
| LMArena WebDev | — | 1400 |
| SciCode | 51.5% | — |
Agentic & Tool Use Not comparable
Muse Spark: —, Qwen3.5 397B-A17B: 33.2 (#51)
| Benchmark | Muse Spark | Qwen3.5 397B-A17B |
|---|---|---|
| APEX-Agents | — | 24.9% |
| τ²-bench Airline | — | 81.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 84.4% |
| τ²-bench Telecom | — | 97.8% |
Reasoning Muse Spark leads
Muse Spark: 34.9 (#61), Qwen3.5 397B-A17B: 33.6 (#62)
| Benchmark | Muse Spark | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Hard Prompts | 1475 | 1448 |
| Epoch Capabilities Index | 152.09 | 146.64 |
| Kagi LLM Benchmark | — | 73.7% |
| NYT Connections (extended) | — | 58.9% |
| CritPt | 11.3% | — |
| Chess Puzzles | — | 13% |
| Thematic Generalization | — | 65.1% |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 87.5% |
| LMCA | — | 37.9% |
Math Muse Spark leads
Muse Spark: 46.8 (#57), Qwen3.5 397B-A17B: 44.9 (#64)
| Benchmark | Muse Spark | Qwen3.5 397B-A17B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 88.9% |
| LMArena Math | 1455 | 1455 |
| FrontierMath (Tiers 1-3) | — | 31.2% |
| ProofBench | 17% | — |
| FrontierMath (Feb 2025 set) | 39% | — |
| FrontierMath Tier 4 (v1) | 14.6% | — |
Knowledge Muse Spark leads
Muse Spark: 65.7 (#12), Qwen3.5 397B-A17B: 53.3 (#53)
| Benchmark | Muse Spark | Qwen3.5 397B-A17B |
|---|---|---|
| GPQA Diamond | 89.8% | 86.4% |
| LMArena Expert | 1458 | 1461 |
| Humanity's Last Exam | 40.6% | — |
Multimodal Muse Spark leads
Muse Spark: 42.7 (#23), Qwen3.5 397B-A17B: 40.0 (#42)
| Benchmark | Muse Spark | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | 1306 | 1262 |
| LMArena Document | 1444 | — |
Multilingual Muse Spark leads
Muse Spark: 56.3 (#23), Qwen3.5 397B-A17B: 54.0 (#56)
| Benchmark | Muse Spark | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | 1464 | 1431 |
| LMArena Chinese | 1507 | 1501 |
| LMArena French | 1497 | 1461 |
| LMArena German | 1497 | 1447 |
| LMArena Korean | 1457 | 1382 |
| LMArena Russian | 1467 | 1429 |
| LMArena Spanish | 1471 | 1443 |
| LMArena Japanese | — | 1427 |
Instruction Following Too close to call
Muse Spark: 76.1 (#47), Qwen3.5 397B-A17B: 75.2 (#73)
| Benchmark | Muse Spark | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | 1443 | 1424 |
Long Context Too close to call
Muse Spark: 44.4 (#65), Qwen3.5 397B-A17B: 44.1 (#71)
| Benchmark | Muse Spark | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | 1451 | 1442 |
Writing & Preference Muse Spark leads
Muse Spark: 66.2 (#37), Qwen3.5 397B-A17B: 62.5 (#74)
| Benchmark | Muse Spark | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | 1474 | 1438 |
| LMArena Creative Writing | 1460 | 1401 |
| LMArena Multi-Turn | 1477 | 1447 |
| EQ-Bench Creative Writing | — | 1478 |
Frequently asked questions
Is Muse Spark better than Qwen3.5 397B-A17B?
Muse Spark is the stronger model overall, scoring 50.3 to 45.7 on the Noometry Index.
Is Muse Spark or Qwen3.5 397B-A17B better for coding?
Muse Spark scores higher on coding benchmarks: 45.6 versus 41.7 in the Noometry coding category.
How many benchmarks do Muse Spark and Qwen3.5 397B-A17B share?
20 benchmarks have published results for both models. Muse Spark has 27 scored results on Noometry and Qwen3.5 397B-A17B has 36.