Model comparison

DBRX vs Muse Spark

Muse Spark is the stronger model overall, scoring 50.6 to 29.4 on the Noometry Index.

Last verified . 17 shared benchmarks.

DBRX Databricks

29.4

Rank #311 Confirmed

Muse Spark Meta

50.6

Rank #46 Confirmed

Summary

  • They share 17 benchmarks with published results for both. DBRX 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 14.9.
  • The biggest single-benchmark swing is GPQA Diamond: 32.9% for DBRX and 89.8% for Muse Spark.
  • DBRX has downloadable open weights; the other is API-only.

Side by side

DBRX and Muse Spark specifications
DBRXMuse Spark
ProviderDatabricksMeta
Noometry Index29.450.6
Released2024-03-272026-04-08
WeightsOpenProprietary
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked2127

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

Category by category

Coding Muse Spark leads

DBRX: 32.9 (#266), Muse Spark: 46.2 (#69)

Coding benchmarks
BenchmarkDBRXMuse Spark
LMArena Coding11321481
SciCode—51.5%
HumanEval+70.1%—
MBPP+55.8%—

Reasoning Muse Spark leads

DBRX: 21.4 (#222), Muse Spark: 35.9 (#67)

Reasoning benchmarks
BenchmarkDBRXMuse Spark
LMArena Hard Prompts11131474
CritPt—11.3%
Epoch Capabilities Index—152.04

Math Muse Spark leads

DBRX: 24.3 (#269), Muse Spark: 47.8 (#66)

Math benchmarks
BenchmarkDBRXMuse Spark
LMArena Math11451455
OTIS Mock AIME 2024-2025—88.9%
ProofBench—17%
MATH Level 511.7%—
FrontierMath (Feb 2025 set)—39%
FrontierMath Tier 4 (v1)—14.6%

Knowledge Muse Spark leads

DBRX: 14.9 (#294), Muse Spark: 65.7 (#13)

Knowledge benchmarks
BenchmarkDBRXMuse Spark
GPQA Diamond32.9%89.8%
LMArena Expert10761457
Humanity's Last Exam—40.6%

Multimodal Not comparable

DBRX: —, Muse Spark: 43.4 (#24)

Multimodal benchmarks
BenchmarkDBRXMuse Spark
LMArena Vision—1306
LMArena Document—1444

Multilingual Muse Spark leads

DBRX: 29.3 (#268), Muse Spark: 56.1 (#24)

Multilingual benchmarks
BenchmarkDBRXMuse Spark
LMArena Non-English10711464
LMArena Chinese10681509
LMArena French10961497
LMArena German10571497
LMArena Korean9931459
LMArena Russian10781466
LMArena Spanish10641472
LMArena Japanese990—

Instruction Following Muse Spark leads

DBRX: 57.5 (#270), Muse Spark: 75.9 (#51)

Instruction Following benchmarks
BenchmarkDBRXMuse Spark
LMArena Instruction Following11121442

Long Context Muse Spark leads

DBRX: 33.7 (#258), Muse Spark: 44.4 (#69)

Long Context benchmarks
BenchmarkDBRXMuse Spark
LMArena Longer Query11121451

Writing & Preference Muse Spark leads

DBRX: 33.6 (#275), Muse Spark: 66.0 (#39)

Writing & Preference benchmarks
BenchmarkDBRXMuse Spark
LMArena Text11191474
LMArena Creative Writing11041459
LMArena Multi-Turn11111477

Frequently asked questions

Is DBRX better than Muse Spark?

Muse Spark is the stronger model overall, scoring 50.6 to 29.4 on the Noometry Index.

Is DBRX or Muse Spark better for coding?

Muse Spark scores higher on coding benchmarks: 46.2 versus 32.9 in the Noometry coding category.

How many benchmarks do DBRX and Muse Spark share?

17 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Muse Spark has 27.

Related comparisons

Go deeper