Noometry

Model comparison

Mixtral 8x22B vs Muse Spark 1.3

Muse Spark 1.3 is the stronger model overall, scoring 54.4 to 26.7 on the Noometry Index.

Last verified . 17 shared benchmarks.

Mixtral 8x22B Mistral AI

26.7

Rank #330 Confirmed

Muse Spark 1.3 Meta

54.4

Rank #27 Confirmed

Summary

  • They share 17 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 72.4 to 21.2.
  • 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 Index26.754.4
Released2024-04-172026-09-02
WeightsOpenProprietary
Context window64K1.05M
Max output64K131K
Input $ / M tokens$2$1.25
Output $ / M tokens$6$4.25
Results tracked3434

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

Category by category

Coding Muse Spark 1.3 leads

Mixtral 8x22B: 23.8 (#324), Muse Spark 1.3: 56.1 (#18)

BenchmarkMixtral 8x22BMuse Spark 1.3
LMArena Coding11661516
CursorBench—41.6%
LMArena WebDev—1655
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: 22.8 (#119), Muse Spark 1.3: 38.6 (#28)

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

Reasoning Muse Spark 1.3 leads

Mixtral 8x22B: 19.1 (#246), Muse Spark 1.3: 52.9 (#27)

BenchmarkMixtral 8x22BMuse Spark 1.3
LMArena Hard Prompts11501503
DTBench55.1%96.5%
Epoch Capabilities Index122156.89
NYT Connections (extended)—85.1%
CritPt—24.9%
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: 21.2 (#271), Muse Spark 1.3: 72.4 (#16)

BenchmarkMixtral 8x22BMuse Spark 1.3
LMArena Math11841497
FrontierMath (Tiers 1-3)—74.4%
FrontierMath Tier 4—46.3%
OTIS Mock AIME 2024-2025—99.2%
Omni-MATH16.3%—
MATH Level 524.2%—

Knowledge Muse Spark 1.3 leads

Mixtral 8x22B: 15.1 (#288), Muse Spark 1.3: 42.0 (#92)

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: 43.0 (#21)

BenchmarkMixtral 8x22BMuse Spark 1.3
LMArena Vision—1310
LMArena Document—1471

Multilingual Muse Spark 1.3 leads

Mixtral 8x22B: 32.9 (#250), Muse Spark 1.3: 57.8 (#6)

BenchmarkMixtral 8x22BMuse Spark 1.3
LMArena Non-English11281485
LMArena Chinese11161527
LMArena French11651534
LMArena Korean10561513
LMArena Russian11581491
LMArena Spanish11501485
LMArena German1141—
LMArena Japanese1037—

Instruction Following Muse Spark 1.3 leads

Mixtral 8x22B: 57.9 (#261), Muse Spark 1.3: 77.8 (#14)

BenchmarkMixtral 8x22BMuse Spark 1.3
LMArena Instruction Following11471481
IFEval72.4%—

Long Context Muse Spark 1.3 leads

Mixtral 8x22B: 34.6 (#242), Muse Spark 1.3: 45.7 (#29)

BenchmarkMixtral 8x22BMuse Spark 1.3
LMArena Longer Query11441491

Writing & Preference Muse Spark 1.3 leads

Mixtral 8x22B: 37.1 (#257), Muse Spark 1.3: 73.7 (#10)

BenchmarkMixtral 8x22BMuse Spark 1.3
LMArena Text11621490
LMArena Creative Writing11411450
LMArena Multi-Turn11301486
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 54.4 to 26.7 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: 56.1 versus 23.8 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?

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

Related comparisons

Go deeper