Noometry

Model comparison

Muse Spark vs Muse Spark 1.3

Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 50.6 on the Noometry Index.

Last verified . 23 shared benchmarks.

Muse Spark Meta

50.6

Rank #46 Confirmed

Muse Spark 1.3 Meta

54.8

Rank #27 Confirmed

Summary

  • They share 23 benchmarks with published results for both. Muse Spark scores higher in 1 category 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 47.8.
  • The biggest single-benchmark swing is ProofBench: 17% for Muse Spark and 58% for Muse Spark 1.3.

Side by side

Muse SparkMuse Spark 1.3
ProviderMetaMeta
Noometry Index50.654.8
Released2026-04-082026-09-02
WeightsProprietaryProprietary
Context window—1.05M
Max output—131K
Input $ / M tokens—$1.25
Output $ / M tokens—$4.25
Results tracked2737

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

Category by category

Coding Muse Spark 1.3 leads

Muse Spark: 46.2 (#69), Muse Spark 1.3: 56.6 (#21)

BenchmarkMuse SparkMuse Spark 1.3
SciCode51.5%59.7%
LMArena Coding14811514
CursorBench—41.6%
LMArena WebDev—1657

Agentic & Tool Use Not comparable

Muse Spark: —, Muse Spark 1.3: 38.6 (#30)

BenchmarkMuse SparkMuse Spark 1.3
APEX-Agents—57.8%
GDP.pdf—27.6%

Reasoning Muse Spark 1.3 leads

Muse Spark: 35.9 (#67), Muse Spark 1.3: 54.0 (#27)

BenchmarkMuse SparkMuse Spark 1.3
CritPt11.3%26%
LMArena Hard Prompts14741503
Epoch Capabilities Index152.04156.75
NYT Connections (extended)—85.1%
Chess Puzzles—38%
Mystery Game Puzzles—25%
DTBench—96.5%
LMCA—53.9%
Bench to the Future 3—0.14

Math Muse Spark 1.3 leads

Muse Spark: 47.8 (#66), Muse Spark 1.3: 73.1 (#21)

BenchmarkMuse SparkMuse Spark 1.3
OTIS Mock AIME 2024-202588.9%99.2%
ProofBench17%58%
LMArena Math14551494
FrontierMath (Tiers 1-3)—74.4%
FrontierMath Tier 4—46.3%
FrontierMath (Feb 2025 set)39%—
FrontierMath Tier 4 (v1)14.6%—

Knowledge Muse Spark leads

Muse Spark: 65.7 (#13), Muse Spark 1.3: 42.6 (#95)

BenchmarkMuse SparkMuse Spark 1.3
LMArena Expert14571516
GPQA Diamond89.8%—
Humanity's Last Exam40.6%—

Multimodal Too close to call

Muse Spark: 43.4 (#24), Muse Spark 1.3: 43.7 (#22)

BenchmarkMuse SparkMuse Spark 1.3
LMArena Vision13061309
LMArena Document14441471

Multilingual Muse Spark 1.3 leads

Muse Spark: 56.1 (#24), Muse Spark 1.3: 57.4 (#8)

BenchmarkMuse SparkMuse Spark 1.3
LMArena Non-English14641481
LMArena Chinese15091529
LMArena French14971524
LMArena German14971515
LMArena Korean14591501
LMArena Russian14661490
LMArena Spanish14721490
LMArena Japanese—1474

Instruction Following Muse Spark 1.3 leads

Muse Spark: 75.9 (#51), Muse Spark 1.3: 77.5 (#22)

BenchmarkMuse SparkMuse Spark 1.3
LMArena Instruction Following14421477

Long Context Muse Spark 1.3 leads

Muse Spark: 44.4 (#69), Muse Spark 1.3: 45.6 (#32)

BenchmarkMuse SparkMuse Spark 1.3
LMArena Longer Query14511488

Writing & Preference Muse Spark 1.3 leads

Muse Spark: 66.0 (#39), Muse Spark 1.3: 73.6 (#9)

BenchmarkMuse SparkMuse Spark 1.3
LMArena Text14741490
LMArena Creative Writing14591455
LMArena Multi-Turn14771482
EQ-Bench Creative Writing—1906

Frequently asked questions

Is Muse Spark better than Muse Spark 1.3?

Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 50.6 on the Noometry Index.

Is Muse Spark or Muse Spark 1.3 better for coding?

Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 46.2 in the Noometry coding category.

How many benchmarks do Muse Spark and Muse Spark 1.3 share?

23 benchmarks have published results for both models. Muse Spark has 27 scored results on Noometry and Muse Spark 1.3 has 37.

Related comparisons

Go deeper