Model comparison

Mistral Small 4 vs Muse Spark 1.1

Muse Spark 1.1 has enough public results to be ranked (#43); Mistral Small 4 does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

Mistral Small 4 Mistral AI

30.2

Unranked Sparse

Muse Spark 1.1 Meta

49.9

Rank #43 Confirmed

Summary

  • The widest gap is in reasoning, where Muse Spark 1.1 leads 45.9 to 21.2.
  • Mistral Small 4 is cheaper at $0.075 / $0.30 per million input/output tokens, against $1.25 / $4.25 for Muse Spark 1.1.
  • Muse Spark 1.1 accepts more context: 1.05M tokens versus 262K.
  • Mistral Small 4 has downloadable open weights; the other is API-only.

Side by side

Mistral Small 4 and Muse Spark 1.1 specifications
Mistral Small 4Muse Spark 1.1
ProviderMistral AIMeta
Noometry Index30.249.9
Released—2026-04-08
WeightsOpenProprietary
Context window262K1.05M
Max output210K131K
Input $ / M tokens$0.075$1.25
Output $ / M tokens$0.30$4.25
Results tracked136

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

Category by category

Coding Not comparable

Mistral Small 4: —, Muse Spark 1.1: 50.8 (#38)

Coding benchmarks
BenchmarkMistral Small 4Muse Spark 1.1
DeepSWE—53.3%
LMArena WebDev—1542
SciCode—58.8%
LMArena Coding—1497

Agentic & Tool Use Not comparable

Mistral Small 4: —, Muse Spark 1.1: 33.9 (#45)

Agentic & Tool Use benchmarks
BenchmarkMistral Small 4Muse Spark 1.1
τ²-bench Banking—40.5%
GBAEval—7.9%
GDP.pdf—15%
Vending-Bench 2—6,520

Reasoning Muse Spark 1.1 leads

Mistral Small 4: 21.2, Muse Spark 1.1: 45.9 (#41)

Reasoning benchmarks
BenchmarkMistral Small 4Muse Spark 1.1
Kagi LLM Benchmark40.5%—
NYT Connections (extended)—84.9%
CritPt—15.1%
LMArena Hard Prompts—1486
DTBench—94.4%
LMCA—49.9%
Surface Evolver Bench—52.5%
Epoch Capabilities Index—154.32

Math Not comparable

Mistral Small 4: —, Muse Spark 1.1: 44.0 (#67)

Math benchmarks
BenchmarkMistral Small 4Muse Spark 1.1
ProofBench—39%
LMArena Math—1477

Knowledge Not comparable

Mistral Small 4: —, Muse Spark 1.1: 52.8 (#55)

Knowledge benchmarks
BenchmarkMistral Small 4Muse Spark 1.1
SimpleQA Verified—57.8%
LMArena Expert—1480

Multimodal Not comparable

Mistral Small 4: —, Muse Spark 1.1: 41.9 (#28)

Multimodal benchmarks
BenchmarkMistral Small 4Muse Spark 1.1
LMArena Vision—1292
LMArena Document—1465

Multilingual Not comparable

Mistral Small 4: —, Muse Spark 1.1: 56.8 (#16)

Multilingual benchmarks
BenchmarkMistral Small 4Muse Spark 1.1
LMArena Non-English—1471
LMArena Chinese—1518
LMArena French—1494
LMArena German—1466
LMArena Japanese—1445
LMArena Korean—1459
LMArena Russian—1482
LMArena Spanish—1471

Instruction Following Not comparable

Mistral Small 4: —, Muse Spark 1.1: 76.8 (#36)

Instruction Following benchmarks
BenchmarkMistral Small 4Muse Spark 1.1
LMArena Instruction Following—1457

Long Context Not comparable

Mistral Small 4: —, Muse Spark 1.1: 44.8 (#55)

Long Context benchmarks
BenchmarkMistral Small 4Muse Spark 1.1
LMArena Longer Query—1463

Writing & Preference Not comparable

Mistral Small 4: —, Muse Spark 1.1: 73.6 (#11)

Writing & Preference benchmarks
BenchmarkMistral Small 4Muse Spark 1.1
LMArena Text—1479
LMArena Creative Writing—1440
EQ-Bench Creative Writing—1927
EQ-Bench 4—1260
LMArena Multi-Turn—1484

Frequently asked questions

Is Mistral Small 4 better than Muse Spark 1.1?

Muse Spark 1.1 has enough public results to be ranked (#43); Mistral Small 4 does not yet, so treat this comparison as directional.

Which is cheaper, Mistral Small 4 or Muse Spark 1.1?

Mistral Small 4 is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; Muse Spark 1.1 lists at $1.25 and $4.25.

Which has the bigger context window?

Muse Spark 1.1 does, with 1.05M tokens against 262K.

How many benchmarks do Mistral Small 4 and Muse Spark 1.1 share?

0 benchmarks have published results for both models. Mistral Small 4 has 1 scored results on Noometry and Muse Spark 1.1 has 36.

Related comparisons

Go deeper