Model comparison

MiMo-V2-Flash vs Muse Spark

Muse Spark is the stronger model overall, scoring 50.6 to 41.3 on the Noometry Index.

Last verified . 18 shared benchmarks.

MiMo-V2-Flash Xiaomi

41.3

Rank #138 Confirmed

Muse Spark Meta

50.6

Rank #46 Confirmed

Summary

  • They share 18 benchmarks with published results for both. MiMo-V2-Flash scores higher in 0 categories and Muse Spark in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Muse Spark leads 65.7 to 39.7.
  • The biggest single-benchmark swing is SciCode: 25.9% for MiMo-V2-Flash and 51.5% for Muse Spark.
  • MiMo-V2-Flash has downloadable open weights; the other is API-only.

Side by side

MiMo-V2-Flash and Muse Spark specifications
MiMo-V2-FlashMuse Spark
ProviderXiaomiMeta
Noometry Index41.350.6
Released2025-12-162026-04-08
WeightsOpenProprietary
Context window262K—
Max output66K—
Input $ / M tokens$0.14—
Output $ / M tokens$0.28—
Results tracked2127

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

Category by category

Coding Muse Spark leads

MiMo-V2-Flash: 36.1 (#211), Muse Spark: 46.2 (#69)

Coding benchmarks
BenchmarkMiMo-V2-FlashMuse Spark
SciCode25.9%51.5%
LMArena Coding14431481
LMArena WebDev1330—
ALE-Bench737.95—

Reasoning Muse Spark leads

MiMo-V2-Flash: 24.9 (#157), Muse Spark: 35.9 (#67)

Reasoning benchmarks
BenchmarkMiMo-V2-FlashMuse Spark
CritPt0%11.3%
LMArena Hard Prompts14201474
Epoch Capabilities Index—152.04

Math Muse Spark leads

MiMo-V2-Flash: 38.3 (#139), Muse Spark: 47.8 (#66)

Math benchmarks
BenchmarkMiMo-V2-FlashMuse Spark
LMArena Math13961455
OTIS Mock AIME 2024-2025—88.9%
ProofBench—17%
FrontierMath (Feb 2025 set)—39%
FrontierMath Tier 4 (v1)—14.6%

Knowledge Muse Spark leads

MiMo-V2-Flash: 39.7 (#131), Muse Spark: 65.7 (#13)

Knowledge benchmarks
BenchmarkMiMo-V2-FlashMuse Spark
LMArena Expert14251457
GPQA Diamond—89.8%
Humanity's Last Exam—40.6%

Multimodal Not comparable

MiMo-V2-Flash: —, Muse Spark: 43.4 (#24)

Multimodal benchmarks
BenchmarkMiMo-V2-FlashMuse Spark
LMArena Vision—1306
LMArena Document—1444

Multilingual Muse Spark leads

MiMo-V2-Flash: 51.0 (#113), Muse Spark: 56.1 (#24)

Multilingual benchmarks
BenchmarkMiMo-V2-FlashMuse Spark
LMArena Non-English13921464
LMArena Chinese14621509
LMArena French14291497
LMArena German13951497
LMArena Korean13581459
LMArena Russian13871466
LMArena Spanish14201472
LMArena Japanese1325—

Instruction Following Muse Spark leads

MiMo-V2-Flash: 73.5 (#120), Muse Spark: 75.9 (#51)

Instruction Following benchmarks
BenchmarkMiMo-V2-FlashMuse Spark
LMArena Instruction Following13921442

Long Context Muse Spark leads

MiMo-V2-Flash: 43.0 (#110), Muse Spark: 44.4 (#69)

Long Context benchmarks
BenchmarkMiMo-V2-FlashMuse Spark
LMArena Longer Query14091451

Writing & Preference Muse Spark leads

MiMo-V2-Flash: 59.7 (#106), Muse Spark: 66.0 (#39)

Writing & Preference benchmarks
BenchmarkMiMo-V2-FlashMuse Spark
LMArena Text14111474
LMArena Creative Writing13751459
LMArena Multi-Turn14041477

Frequently asked questions

Is MiMo-V2-Flash better than Muse Spark?

Muse Spark is the stronger model overall, scoring 50.6 to 41.3 on the Noometry Index.

Is MiMo-V2-Flash or Muse Spark better for coding?

Muse Spark scores higher on coding benchmarks: 46.2 versus 36.1 in the Noometry coding category.

How many benchmarks do MiMo-V2-Flash and Muse Spark share?

18 benchmarks have published results for both models. MiMo-V2-Flash has 21 scored results on Noometry and Muse Spark has 27.

Related comparisons

Go deeper