Noometry

Model comparison

C4ai Aya Expanse 32b vs Muse Spark 1.3

Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 35.9 on the Noometry Index.

Last verified . 17 shared benchmarks.

C4ai Aya Expanse 32b Cohere

35.9

Rank #221 Confirmed

Muse Spark 1.3 Meta

54.8

Rank #27 Confirmed

Summary

  • They share 17 benchmarks with published results for both. C4ai Aya Expanse 32b scores higher in 0 categories and Muse Spark 1.3 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Muse Spark 1.3 leads 73.1 to 34.0.
  • Muse Spark 1.3 accepts more context: 1.05M tokens versus 128K.
  • C4ai Aya Expanse 32b has downloadable open weights; the other is API-only.

Side by side

C4ai Aya Expanse 32bMuse Spark 1.3
ProviderCohereMeta
Noometry Index35.954.8
Released2024-10-242026-09-02
WeightsOpenProprietary
Context window128K1.05M
Max output4K131K
Input $ / M tokens—$1.25
Output $ / M tokens—$4.25
Results tracked1837

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

Category by category

Coding Muse Spark 1.3 leads

C4ai Aya Expanse 32b: 34.8 (#231), Muse Spark 1.3: 56.6 (#21)

BenchmarkC4ai Aya Expanse 32bMuse Spark 1.3
LMArena Coding11971514
CursorBench—41.6%
LMArena WebDev—1657
SciCode—59.7%

Agentic & Tool Use Not comparable

C4ai Aya Expanse 32b: —, Muse Spark 1.3: 38.6 (#30)

BenchmarkC4ai Aya Expanse 32bMuse Spark 1.3
APEX-Agents—57.8%
GDP.pdf—27.6%

Reasoning Muse Spark 1.3 leads

C4ai Aya Expanse 32b: 23.3 (#180), Muse Spark 1.3: 54.0 (#27)

BenchmarkC4ai Aya Expanse 32bMuse Spark 1.3
LMArena Hard Prompts11931503
NYT Connections (extended)—85.1%
CritPt—26%
Chess Puzzles—38%
Mystery Game Puzzles—25%
DTBench—96.5%
LMCA—53.9%
Bench to the Future 3—0.14
Epoch Capabilities Index—156.75

Math Muse Spark 1.3 leads

C4ai Aya Expanse 32b: 34.0 (#197), Muse Spark 1.3: 73.1 (#21)

BenchmarkC4ai Aya Expanse 32bMuse Spark 1.3
LMArena Math12001494
FrontierMath (Tiers 1-3)—74.4%
FrontierMath Tier 4—46.3%
OTIS Mock AIME 2024-2025—99.2%
ProofBench—58%

Knowledge Muse Spark 1.3 leads

C4ai Aya Expanse 32b: 33.2 (#206), Muse Spark 1.3: 42.6 (#95)

BenchmarkC4ai Aya Expanse 32bMuse Spark 1.3
LMArena Expert11821516
Vectara Hallucination Rate10.9%—

Multimodal Not comparable

C4ai Aya Expanse 32b: —, Muse Spark 1.3: 43.7 (#22)

BenchmarkC4ai Aya Expanse 32bMuse Spark 1.3
LMArena Vision—1309
LMArena Document—1471

Multilingual Muse Spark 1.3 leads

C4ai Aya Expanse 32b: 38.4 (#230), Muse Spark 1.3: 57.4 (#8)

BenchmarkC4ai Aya Expanse 32bMuse Spark 1.3
LMArena Non-English12131481
LMArena Chinese12111529
LMArena French12481524
LMArena German11991515
LMArena Japanese11631474
LMArena Korean11581501
LMArena Russian12271490
LMArena Spanish11931490

Instruction Following Muse Spark 1.3 leads

C4ai Aya Expanse 32b: 62.6 (#237), Muse Spark 1.3: 77.5 (#22)

BenchmarkC4ai Aya Expanse 32bMuse Spark 1.3
LMArena Instruction Following11961477

Long Context Muse Spark 1.3 leads

C4ai Aya Expanse 32b: 37.2 (#220), Muse Spark 1.3: 45.6 (#32)

BenchmarkC4ai Aya Expanse 32bMuse Spark 1.3
LMArena Longer Query12281488

Writing & Preference Muse Spark 1.3 leads

C4ai Aya Expanse 32b: 42.2 (#235), Muse Spark 1.3: 73.6 (#9)

BenchmarkC4ai Aya Expanse 32bMuse Spark 1.3
LMArena Text12241490
LMArena Creative Writing12001455
LMArena Multi-Turn11901482
EQ-Bench Creative Writing—1906

Frequently asked questions

Is C4ai Aya Expanse 32b better than Muse Spark 1.3?

Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 35.9 on the Noometry Index.

Is C4ai Aya Expanse 32b or Muse Spark 1.3 better for coding?

Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 34.8 in the Noometry coding category.

Which has the bigger context window?

Muse Spark 1.3 does, with 1.05M tokens against 128K.

How many benchmarks do C4ai Aya Expanse 32b and Muse Spark 1.3 share?

17 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Muse Spark 1.3 has 37.

Related comparisons

Go deeper