Noometry

Model comparison

Llama 2-70B vs Muse Spark 1.3

Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 24.4 on the Noometry Index.

Last verified . 20 shared benchmarks.

Llama 2-70B Meta

24.4

Rank #349 Confirmed

Muse Spark 1.3 Meta

54.8

Rank #27 Confirmed

Summary

  • They share 20 benchmarks with published results for both. Llama 2-70B scores higher in 0 categories and Muse Spark 1.3 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Muse Spark 1.3 leads 73.1 to 8.1.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0% for Llama 2-70B and 99.2% for Muse Spark 1.3.
  • Llama 2-70B has downloadable open weights; the other is API-only.

Side by side

Llama 2-70BMuse Spark 1.3
ProviderMetaMeta
Noometry Index24.454.8
Released2023-07-182026-09-02
WeightsOpenProprietary
Context window—1.05M
Max output—131K
Input $ / M tokens—$1.25
Output $ / M tokens—$4.25
Results tracked3537

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

Category by category

Coding Muse Spark 1.3 leads

Llama 2-70B: 31.4 (#286), Muse Spark 1.3: 56.6 (#21)

BenchmarkLlama 2-70BMuse Spark 1.3
LMArena Coding10791514
CursorBench—41.6%
LMArena WebDev—1657
SciCode—59.7%

Agentic & Tool Use Not comparable

Llama 2-70B: —, Muse Spark 1.3: 38.6 (#30)

BenchmarkLlama 2-70BMuse Spark 1.3
APEX-Agents—57.8%
GDP.pdf—27.6%

Reasoning Muse Spark 1.3 leads

Llama 2-70B: 14.4 (#325), Muse Spark 1.3: 54.0 (#27)

BenchmarkLlama 2-70BMuse Spark 1.3
LMArena Hard Prompts10731503
DTBench41.6%96.5%
Epoch Capabilities Index113.79156.75
NYT Connections (extended)—85.1%
CritPt—26%
Chess Puzzles—38%
Mystery Game Puzzles—25%
LMCA—53.9%
Bench to the Future 3—0.14
BIG-Bench Hard64.9%—
CommonsenseQA 2.050%—
ForecastBench51.4—
HellaSwag85.3%—
LAMBADA78.9%—
PIQA82.8%—
WinoGrande80.2%—

Math Muse Spark 1.3 leads

Llama 2-70B: 8.1 (#326), Muse Spark 1.3: 73.1 (#21)

BenchmarkLlama 2-70BMuse Spark 1.3
OTIS Mock AIME 2024-20250%99.2%
LMArena Math10911494
FrontierMath (Tiers 1-3)—74.4%
FrontierMath Tier 4—46.3%
ProofBench—58%
MATH Level 53.3%—
GSM8K69.6%—

Knowledge Muse Spark 1.3 leads

Llama 2-70B: 7.4 (#310), Muse Spark 1.3: 42.6 (#95)

BenchmarkLlama 2-70BMuse Spark 1.3
LMArena Expert10391516
GPQA Diamond26.3%—
ARC (AI2) Challenge78.3%—
BoolQ88.6%—
MMLU69.9%—
OpenBookQA60.2%—
TriviaQA87.6%—

Multimodal Not comparable

Llama 2-70B: —, Muse Spark 1.3: 43.7 (#22)

BenchmarkLlama 2-70BMuse Spark 1.3
LMArena Vision—1309
LMArena Document—1471

Multilingual Muse Spark 1.3 leads

Llama 2-70B: 27.7 (#274), Muse Spark 1.3: 57.4 (#8)

BenchmarkLlama 2-70BMuse Spark 1.3
LMArena Non-English10451481
LMArena Chinese9951529
LMArena French10901524
LMArena German10411515
LMArena Japanese9271474
LMArena Korean9641501
LMArena Russian10831490
LMArena Spanish11431490

Instruction Following Muse Spark 1.3 leads

Llama 2-70B: 54.9 (#278), Muse Spark 1.3: 77.5 (#22)

BenchmarkLlama 2-70BMuse Spark 1.3
LMArena Instruction Following10711477

Long Context Muse Spark 1.3 leads

Llama 2-70B: 32.3 (#270), Muse Spark 1.3: 45.6 (#32)

BenchmarkLlama 2-70BMuse Spark 1.3
LMArena Longer Query10621488

Writing & Preference Muse Spark 1.3 leads

Llama 2-70B: 32.3 (#279), Muse Spark 1.3: 73.6 (#9)

BenchmarkLlama 2-70BMuse Spark 1.3
LMArena Text11151490
LMArena Creative Writing10751455
LMArena Multi-Turn10881482
EQ-Bench Creative Writing—1906

Frequently asked questions

Is Llama 2-70B better than Muse Spark 1.3?

Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 24.4 on the Noometry Index.

Is Llama 2-70B or Muse Spark 1.3 better for coding?

Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 31.4 in the Noometry coding category.

How many benchmarks do Llama 2-70B and Muse Spark 1.3 share?

20 benchmarks have published results for both models. Llama 2-70B has 35 scored results on Noometry and Muse Spark 1.3 has 37.

Related comparisons

Go deeper