Noometry

Model comparison

Muse Spark vs Qwen3.5 122B-A10B

Muse Spark is the stronger model overall, scoring 50.6 to 42.1 on the Noometry Index.

Last verified . 19 shared benchmarks.

Muse Spark Meta

50.6

Rank #46 Confirmed

Qwen3.5 122B-A10B Alibaba (Qwen)

42.1

Rank #119 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Muse Spark scores higher in 9 categories and Qwen3.5 122B-A10B in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Muse Spark leads 65.7 to 38.8.
  • The biggest single-benchmark swing is SciCode: 51.5% for Muse Spark and 35.6% for Qwen3.5 122B-A10B.
  • Qwen3.5 122B-A10B has downloadable open weights; the other is API-only.

Side by side

Muse SparkQwen3.5 122B-A10B
ProviderMetaAlibaba (Qwen)
Noometry Index50.642.1
Released2026-04-082026-02-23
WeightsProprietaryOpen
Context window—262K
Max output—66K
Input $ / M tokens—$0.40
Output $ / M tokens—$3.20
Results tracked2727

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Muse Spark leads

Muse Spark: 46.2 (#69), Qwen3.5 122B-A10B: 39.1 (#162)

BenchmarkMuse SparkQwen3.5 122B-A10B
SciCode51.5%35.6%
LMArena Coding14811436
LMArena WebDev—1360

Reasoning Muse Spark leads

Muse Spark: 35.9 (#67), Qwen3.5 122B-A10B: 27.2 (#123)

BenchmarkMuse SparkQwen3.5 122B-A10B
CritPt11.3%0.9%
LMArena Hard Prompts14741421
NYT Connections (extended)—51.7%
Thematic Generalization—51.2%
Mystery Game Puzzles—17%
DTBench—84.3%
LMCA—32.2%
Epoch Capabilities Index152.04—

Math Muse Spark leads

Muse Spark: 47.8 (#66), Qwen3.5 122B-A10B: 39.1 (#112)

BenchmarkMuse SparkQwen3.5 122B-A10B
LMArena Math14551432
OTIS Mock AIME 2024-202588.9%—
ProofBench17%—
FrontierMath (Feb 2025 set)39%—
FrontierMath Tier 4 (v1)14.6%—

Knowledge Muse Spark leads

Muse Spark: 65.7 (#13), Qwen3.5 122B-A10B: 38.8 (#142)

BenchmarkMuse SparkQwen3.5 122B-A10B
LMArena Expert14571432
GPQA Diamond89.8%—
Humanity's Last Exam40.6%—
Vectara Hallucination Rate—11.2%

Multimodal Muse Spark leads

Muse Spark: 43.4 (#24), Qwen3.5 122B-A10B: 39.6 (#57)

BenchmarkMuse SparkQwen3.5 122B-A10B
LMArena Vision13061245
LMArena Document1444—

Multilingual Muse Spark leads

Muse Spark: 56.1 (#24), Qwen3.5 122B-A10B: 51.6 (#107)

BenchmarkMuse SparkQwen3.5 122B-A10B
LMArena Non-English14641400
LMArena Chinese15091462
LMArena French14971442
LMArena German14971426
LMArena Korean14591352
LMArena Russian14661400
LMArena Spanish14721424
LMArena Japanese—1367

Instruction Following Muse Spark leads

Muse Spark: 75.9 (#51), Qwen3.5 122B-A10B: 73.8 (#115)

BenchmarkMuse SparkQwen3.5 122B-A10B
LMArena Instruction Following14421399

Long Context Muse Spark leads

Muse Spark: 44.4 (#69), Qwen3.5 122B-A10B: 43.0 (#109)

BenchmarkMuse SparkQwen3.5 122B-A10B
LMArena Longer Query14511410

Writing & Preference Muse Spark leads

Muse Spark: 66.0 (#39), Qwen3.5 122B-A10B: 60.0 (#105)

BenchmarkMuse SparkQwen3.5 122B-A10B
LMArena Text14741417
LMArena Creative Writing14591368
LMArena Multi-Turn14771416

Frequently asked questions

Is Muse Spark better than Qwen3.5 122B-A10B?

Muse Spark is the stronger model overall, scoring 50.6 to 42.1 on the Noometry Index.

Is Muse Spark or Qwen3.5 122B-A10B better for coding?

Muse Spark scores higher on coding benchmarks: 46.2 versus 39.1 in the Noometry coding category.

How many benchmarks do Muse Spark and Qwen3.5 122B-A10B share?

19 benchmarks have published results for both models. Muse Spark has 27 scored results on Noometry and Qwen3.5 122B-A10B has 27.

Related comparisons

Go deeper