Noometry

Model comparison

Llama 3.1-405B vs Muse Spark 1.2

Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 30.7 on the Noometry Index.

Last verified . 19 shared benchmarks.

Llama 3.1-405B Meta

30.7

Rank #288 Confirmed

Muse Spark 1.2 Meta

50.3

Rank #48 Confirmed

Summary

  • They share 19 benchmarks with published results for both. Llama 3.1-405B scores higher in 0 categories and Muse Spark 1.2 in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Muse Spark 1.2 leads 51.3 to 16.8.
  • The biggest single-benchmark swing is SimpleBench: 23% for Llama 3.1-405B and 74.5% for Muse Spark 1.2.
  • Llama 3.1-405B has downloadable open weights; the other is API-only.

Side by side

Llama 3.1-405BMuse Spark 1.2
ProviderMetaMeta
Noometry Index30.750.3
Released2024-07-232026-08-05
WeightsOpenProprietary
Context window—1.05M
Max output—131K
Input $ / M tokens—$1.25
Output $ / M tokens—$4.25
Results tracked4231

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

Category by category

Coding Muse Spark 1.2 leads

Llama 3.1-405B: 33.1 (#262), Muse Spark 1.2: 49.2 (#51)

BenchmarkLlama 3.1-405BMuse Spark 1.2
WeirdML21.4%60.3%
LMArena Coding12911495
DeepSWE—54.9%
LMArena WebDev—1533
FrontierSWE—12%
SciCode—56.4%

Agentic & Tool Use Muse Spark 1.2 leads

Llama 3.1-405B: 21.0 (#140), Muse Spark 1.2: 29.4 (#87)

BenchmarkLlama 3.1-405BMuse Spark 1.2
APEX-Agents—36.4%
TheAgentCompany7.4%—
Cybench7.5%—
GDP.pdf—16%

Reasoning Muse Spark 1.2 leads

Llama 3.1-405B: 16.8 (#300), Muse Spark 1.2: 51.3 (#34)

BenchmarkLlama 3.1-405BMuse Spark 1.2
SimpleBench23%74.5%
LMArena Hard Prompts12691486
DTBench61.4%94.7%
Epoch Capabilities Index128.75154.87
Kagi LLM Benchmark45%—
NYT Connections (extended)—79.2%
CritPt—17.7%
LMCA—48.4%
BIG-Bench Hard82.9%—
ForecastBench59.9—
HellaSwag89.2%—
PIQA85.9%—
WinoGrande89.2%—

Math Muse Spark 1.2 leads

Llama 3.1-405B: 18.4 (#290), Muse Spark 1.2: 46.4 (#70)

BenchmarkLlama 3.1-405BMuse Spark 1.2
LMArena Math12811471
OTIS Mock AIME 2024-20259.7%—
ProofBench—43%
Omni-MATH24.9%—
MATH Level 549.8%—

Knowledge Muse Spark 1.2 leads

Llama 3.1-405B: 30.4 (#227), Muse Spark 1.2: 54.1 (#53)

BenchmarkLlama 3.1-405BMuse Spark 1.2
LMArena Expert12431480
GPQA Diamond50.9%—
SimpleQA Verified—60.3%
MMLU-Pro72.3%—
Confabulations17.6%—
GPQA (HELM)52.2%—
ARC (AI2) Challenge95.3%—
MMLU84.5%—
TriviaQA82.7%—

Multimodal Not comparable

Llama 3.1-405B: —, Muse Spark 1.2: 43.4 (#25)

BenchmarkLlama 3.1-405BMuse Spark 1.2
LMArena Vision—1305

Multilingual Muse Spark 1.2 leads

Llama 3.1-405B: 40.7 (#214), Muse Spark 1.2: 57.1 (#11)

BenchmarkLlama 3.1-405BMuse Spark 1.2
LMArena Non-English12481478
LMArena Chinese12421511
LMArena French12791513
LMArena Russian12651487
LMArena Spanish12601498
LMArena German1252—
LMArena Japanese1208—
LMArena Korean1184—

Instruction Following Muse Spark 1.2 leads

Llama 3.1-405B: 65.9 (#214), Muse Spark 1.2: 76.7 (#36)

BenchmarkLlama 3.1-405BMuse Spark 1.2
LMArena Instruction Following12591461
IFEval81.1%—

Long Context Muse Spark 1.2 leads

Llama 3.1-405B: 38.4 (#197), Muse Spark 1.2: 45.2 (#48)

BenchmarkLlama 3.1-405BMuse Spark 1.2
LMArena Longer Query12661475

Writing & Preference Muse Spark 1.2 leads

Llama 3.1-405B: 38.9 (#251), Muse Spark 1.2: 72.3 (#14)

BenchmarkLlama 3.1-405BMuse Spark 1.2
LMArena Text12841482
LMArena Creative Writing12621449
EQ-Bench Creative Writing8701840
LMArena Multi-Turn12971494
WildBench78.3%—

Frequently asked questions

Is Llama 3.1-405B better than Muse Spark 1.2?

Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 30.7 on the Noometry Index.

Is Llama 3.1-405B or Muse Spark 1.2 better for coding?

Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 33.1 in the Noometry coding category.

How many benchmarks do Llama 3.1-405B and Muse Spark 1.2 share?

19 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and Muse Spark 1.2 has 31.

Related comparisons

Go deeper