Noometry

Model comparison

Mixtral 8x22B vs Muse Spark 1.3

Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 27.1 on the Noometry Index.

Last verified . 19 shared benchmarks.

Mixtral 8x22B Mistral AI

27.1

Rank #333 Confirmed

Muse Spark 1.3 Meta

54.8

Rank #27 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Mixtral 8x22B scores higher in 0 categories and Muse Spark 1.3 in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Muse Spark 1.3 leads 73.1 to 22.9.
  • The biggest single-benchmark swing is DTBench: 55.1% for Mixtral 8x22B and 96.5% for Muse Spark 1.3.
  • Muse Spark 1.3 is cheaper at $1.25 / $4.25 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
  • Muse Spark 1.3 accepts more context: 1.05M tokens versus 64K.
  • Mixtral 8x22B has downloadable open weights; the other is API-only.

Side by side

Mixtral 8x22BMuse Spark 1.3
ProviderMistral AIMeta
Noometry Index27.154.8
Released2024-04-172026-09-02
WeightsOpenProprietary
Context window64K1.05M
Max output64K131K
Input $ / M tokens$2$1.25
Output $ / M tokens$6$4.25
Results tracked3437

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

Category by category

Coding Muse Spark 1.3 leads

Mixtral 8x22B: 24.2 (#329), Muse Spark 1.3: 56.6 (#21)

BenchmarkMixtral 8x22BMuse Spark 1.3
LMArena Coding11661514
CursorBench—41.6%
LMArena WebDev—1657
SciCode—59.7%
WeirdML3.2%—
BigCodeBench Instruct40.6%—
BigCodeBench Complete50.2%—
HumanEval+72%—
MBPP+64.3%—

Agentic & Tool Use Muse Spark 1.3 leads

Mixtral 8x22B: 23.1 (#127), Muse Spark 1.3: 38.6 (#30)

BenchmarkMixtral 8x22BMuse Spark 1.3
APEX-Agents—57.8%
Cybench7.5%—
GDP.pdf—27.6%

Reasoning Muse Spark 1.3 leads

Mixtral 8x22B: 19.9 (#248), Muse Spark 1.3: 54.0 (#27)

BenchmarkMixtral 8x22BMuse Spark 1.3
LMArena Hard Prompts11501503
DTBench55.1%96.5%
Epoch Capabilities Index122.03156.75
NYT Connections (extended)—85.1%
CritPt—26%
Chess Puzzles—38%
Mystery Game Puzzles—25%
LMCA—53.9%
Bench to the Future 3—0.14
ForecastBench56.3—

Math Muse Spark 1.3 leads

Mixtral 8x22B: 22.9 (#275), Muse Spark 1.3: 73.1 (#21)

BenchmarkMixtral 8x22BMuse Spark 1.3
LMArena Math11841494
FrontierMath (Tiers 1-3)—74.4%
FrontierMath Tier 4—46.3%
OTIS Mock AIME 2024-2025—99.2%
ProofBench—58%
Omni-MATH16.3%—
MATH Level 524.2%—

Knowledge Muse Spark 1.3 leads

Mixtral 8x22B: 15.1 (#293), Muse Spark 1.3: 42.6 (#95)

BenchmarkMixtral 8x22BMuse Spark 1.3
LMArena Expert11131516
GPQA Diamond34.1%—
MMLU-Pro46%—
GPQA (HELM)33.4%—
MMLU77.8%—

Multimodal Not comparable

Mixtral 8x22B: —, Muse Spark 1.3: 43.7 (#22)

BenchmarkMixtral 8x22BMuse Spark 1.3
LMArena Vision—1309
LMArena Document—1471

Multilingual Muse Spark 1.3 leads

Mixtral 8x22B: 32.8 (#255), Muse Spark 1.3: 57.4 (#8)

BenchmarkMixtral 8x22BMuse Spark 1.3
LMArena Non-English11281481
LMArena Chinese11161529
LMArena French11661524
LMArena German11411515
LMArena Japanese10371474
LMArena Korean10571501
LMArena Russian11581490
LMArena Spanish11511490

Instruction Following Muse Spark 1.3 leads

Mixtral 8x22B: 57.7 (#266), Muse Spark 1.3: 77.5 (#22)

BenchmarkMixtral 8x22BMuse Spark 1.3
LMArena Instruction Following11471477
IFEval72.4%—

Long Context Muse Spark 1.3 leads

Mixtral 8x22B: 34.7 (#247), Muse Spark 1.3: 45.6 (#32)

BenchmarkMixtral 8x22BMuse Spark 1.3
LMArena Longer Query11441488

Writing & Preference Muse Spark 1.3 leads

Mixtral 8x22B: 36.9 (#262), Muse Spark 1.3: 73.6 (#9)

BenchmarkMixtral 8x22BMuse Spark 1.3
LMArena Text11621490
LMArena Creative Writing11411455
LMArena Multi-Turn11301482
EQ-Bench Creative Writing—1906
WildBench71.1%—

Frequently asked questions

Is Mixtral 8x22B better than Muse Spark 1.3?

Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 27.1 on the Noometry Index.

Which is cheaper, Mixtral 8x22B or Muse Spark 1.3?

Muse Spark 1.3 is cheaper. It lists at $1.25 per million input tokens and $4.25 per million output tokens; Mixtral 8x22B lists at $2 and $6.

Is Mixtral 8x22B or Muse Spark 1.3 better for coding?

Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 24.2 in the Noometry coding category.

Which has the bigger context window?

Muse Spark 1.3 does, with 1.05M tokens against 64K.

How many benchmarks do Mixtral 8x22B and Muse Spark 1.3 share?

19 benchmarks have published results for both models. Mixtral 8x22B has 34 scored results on Noometry and Muse Spark 1.3 has 37.

Related comparisons

Go deeper