Model comparison

MiniMax-M3 vs Muse Spark

Muse Spark is the stronger model overall, scoring 50.6 to 43.8 on the Noometry Index.

Last verified . 24 shared benchmarks.

MiniMax-M3 MiniMax

43.8

Rank #85 Confirmed

Muse Spark Meta

50.6

Rank #46 Confirmed

Summary

  • They share 24 benchmarks with published results for both. MiniMax-M3 scores higher in 0 categories and Muse Spark in 9 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Muse Spark leads 47.8 to 40.0.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 71.1% for MiniMax-M3 and 88.9% for Muse Spark.
  • MiniMax-M3 has downloadable open weights; the other is API-only.

Side by side

MiniMax-M3 and Muse Spark specifications
MiniMax-M3Muse Spark
ProviderMiniMaxMeta
Noometry Index43.850.6
Released2026-06-012026-04-08
WeightsOpenProprietary
Context window1M—
Max output512K—
Input $ / M tokens$0.30—
Output $ / M tokens$1.20—
Results tracked4127

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

Category by category

Coding Muse Spark leads

MiniMax-M3: 41.8 (#118), Muse Spark: 46.2 (#69)

Coding benchmarks
BenchmarkMiniMax-M3Muse Spark
SciCode47.1%51.5%
LMArena Coding14691481
FrontierCode14.7%—
LMArena WebDev1482—
ALE-Bench640.02—

Agentic & Tool Use Not comparable

MiniMax-M3: 22.6 (#130), Muse Spark: —

Agentic & Tool Use benchmarks
BenchmarkMiniMax-M3Muse Spark
APEX-Agents37.7%—
OSWorld 2.04.6%—
GBAEval0.9%—
Vending-Bench 22,158—

Reasoning Muse Spark leads

MiniMax-M3: 30.1 (#87), Muse Spark: 35.9 (#67)

Reasoning benchmarks
BenchmarkMiniMax-M3Muse Spark
CritPt3.7%11.3%
LMArena Hard Prompts14471474
Epoch Capabilities Index146.95152.04
SimpleBench45.8%—
NYT Connections (extended)65.1%—
Chess Puzzles14%—
Mystery Game Puzzles8%—
DTBench78.9%—
LMCA33.7%—
Surface Evolver Bench55%—
ForecastBench61.4—

Math Muse Spark leads

MiniMax-M3: 40.0 (#95), Muse Spark: 47.8 (#66)

Math benchmarks
BenchmarkMiniMax-M3Muse Spark
OTIS Mock AIME 2024-202571.1%88.9%
ProofBench18%17%
LMArena Math14291455
FrontierMath (Feb 2025 set)—39%
FrontierMath Tier 4 (v1)—14.6%

Knowledge Muse Spark leads

MiniMax-M3: 58.4 (#35), Muse Spark: 65.7 (#13)

Knowledge benchmarks
BenchmarkMiniMax-M3Muse Spark
GPQA Diamond90.9%89.8%
LMArena Expert14611457
Humanity's Last Exam—40.6%

Multimodal Muse Spark leads

MiniMax-M3: 40.2 (#51), Muse Spark: 43.4 (#24)

Multimodal benchmarks
BenchmarkMiniMax-M3Muse Spark
LMArena Vision12531306
LMArena Document14351444

Multilingual Muse Spark leads

MiniMax-M3: 53.0 (#75), Muse Spark: 56.1 (#24)

Multilingual benchmarks
BenchmarkMiniMax-M3Muse Spark
LMArena Non-English14201464
LMArena Chinese14631509
LMArena French14471497
LMArena German14261497
LMArena Korean13721459
LMArena Russian14281466
LMArena Spanish14321472
LMArena Japanese1381—

Instruction Following Too close to call

MiniMax-M3: 75.5 (#62), Muse Spark: 75.9 (#51)

Instruction Following benchmarks
BenchmarkMiniMax-M3Muse Spark
LMArena Instruction Following14331442

Long Context Too close to call

MiniMax-M3: 44.2 (#72), Muse Spark: 44.4 (#69)

Long Context benchmarks
BenchmarkMiniMax-M3Muse Spark
LMArena Longer Query14451451

Writing & Preference Muse Spark leads

MiniMax-M3: 62.1 (#83), Muse Spark: 66.0 (#39)

Writing & Preference benchmarks
BenchmarkMiniMax-M3Muse Spark
LMArena Text14331474
LMArena Creative Writing14041459
LMArena Multi-Turn14421477
EQ-Bench 41150—

Frequently asked questions

Is MiniMax-M3 better than Muse Spark?

Muse Spark is the stronger model overall, scoring 50.6 to 43.8 on the Noometry Index.

Is MiniMax-M3 or Muse Spark better for coding?

Muse Spark scores higher on coding benchmarks: 46.2 versus 41.8 in the Noometry coding category.

How many benchmarks do MiniMax-M3 and Muse Spark share?

24 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and Muse Spark has 27.

Related comparisons

Go deeper