Noometry

Model comparison

Devstral Medium vs Muse Spark 1.2

Muse Spark 1.2 has enough public results to be ranked (#48); Devstral Medium does not yet, so treat this comparison as directional.

Last verified . 1 shared benchmarks.

Devstral Medium Mistral AI

30.1

Unranked Sparse

Muse Spark 1.2 Meta

50.3

Rank #48 Confirmed

Summary

  • They share 1 benchmark with published results for both. Devstral Medium scores higher in 0 categories and Muse Spark 1.2 in 2 categories; 2 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Muse Spark 1.2 leads 51.3 to 21.1.
  • Devstral Medium is cheaper at $0.40 / $2 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.2.
  • Muse Spark 1.2 accepts more context: 1.05M tokens versus 262K.
  • Devstral Medium has downloadable open weights; the other is API-only.

Side by side

Devstral MediumMuse Spark 1.2
ProviderMistral AIMeta
Noometry Index30.150.3
Released2025-07-102026-08-05
WeightsOpenProprietary
Context window262K1.05M
Max output262K131K
Input $ / M tokens$0.40$1.25
Output $ / M tokens$2$4.25
Results tracked231

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

Category by category

Coding Muse Spark 1.2 leads

Devstral Medium: 24.3, Muse Spark 1.2: 49.2 (#51)

BenchmarkDevstral MediumMuse Spark 1.2
LMArena WebDev10761533
DeepSWE—54.9%
FrontierSWE—12%
SciCode—56.4%
WeirdML—60.3%
LMArena Coding—1495

Agentic & Tool Use Not comparable

Devstral Medium: —, Muse Spark 1.2: 29.4 (#87)

BenchmarkDevstral MediumMuse Spark 1.2
APEX-Agents—36.4%
GDP.pdf—16%

Reasoning Muse Spark 1.2 leads

Devstral Medium: 21.1, Muse Spark 1.2: 51.3 (#34)

BenchmarkDevstral MediumMuse Spark 1.2
SimpleBench—74.5%
Kagi LLM Benchmark37.7%—
NYT Connections (extended)—79.2%
CritPt—17.7%
LMArena Hard Prompts—1486
DTBench—94.7%
LMCA—48.4%
Epoch Capabilities Index—154.87

Math Not comparable

Devstral Medium: —, Muse Spark 1.2: 46.4 (#70)

BenchmarkDevstral MediumMuse Spark 1.2
ProofBench—43%
LMArena Math—1471

Knowledge Not comparable

Devstral Medium: —, Muse Spark 1.2: 54.1 (#53)

BenchmarkDevstral MediumMuse Spark 1.2
SimpleQA Verified—60.3%
LMArena Expert—1480

Multimodal Not comparable

Devstral Medium: —, Muse Spark 1.2: 43.4 (#25)

BenchmarkDevstral MediumMuse Spark 1.2
LMArena Vision—1305

Multilingual Not comparable

Devstral Medium: —, Muse Spark 1.2: 57.1 (#11)

BenchmarkDevstral MediumMuse Spark 1.2
LMArena Non-English—1478
LMArena Chinese—1511
LMArena French—1513
LMArena Russian—1487
LMArena Spanish—1498

Instruction Following Not comparable

Devstral Medium: —, Muse Spark 1.2: 76.7 (#36)

BenchmarkDevstral MediumMuse Spark 1.2
LMArena Instruction Following—1461

Long Context Not comparable

Devstral Medium: —, Muse Spark 1.2: 45.2 (#48)

BenchmarkDevstral MediumMuse Spark 1.2
LMArena Longer Query—1475

Writing & Preference Not comparable

Devstral Medium: —, Muse Spark 1.2: 72.3 (#14)

BenchmarkDevstral MediumMuse Spark 1.2
LMArena Text—1482
LMArena Creative Writing—1449
EQ-Bench Creative Writing—1840
LMArena Multi-Turn—1494

Frequently asked questions

Is Devstral Medium better than Muse Spark 1.2?

Muse Spark 1.2 has enough public results to be ranked (#48); Devstral Medium does not yet, so treat this comparison as directional.

Which is cheaper, Devstral Medium or Muse Spark 1.2?

Devstral Medium is cheaper. It lists at $0.40 per million input tokens and $2 per million output tokens; Muse Spark 1.2 lists at $1.25 and $4.25.

Is Devstral Medium or Muse Spark 1.2 better for coding?

Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 24.3 in the Noometry coding category.

Which has the bigger context window?

Muse Spark 1.2 does, with 1.05M tokens against 262K.

How many benchmarks do Devstral Medium and Muse Spark 1.2 share?

1 benchmark has published results for both models. Devstral Medium has 2 scored results on Noometry and Muse Spark 1.2 has 31.

Related comparisons

Go deeper