Noometry

Model comparison

GPT-4 vs Muse Spark 1.3

Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 29.1 on the Noometry Index.

Last verified . 24 shared benchmarks.

GPT-4 OpenAI

29.1

Rank #316 Confirmed

Muse Spark 1.3 Meta

54.8

Rank #27 Confirmed

Summary

  • They share 24 benchmarks with published results for both. GPT-4 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 10.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.1% for GPT-4 and 99.2% for Muse Spark 1.3.
  • Muse Spark 1.3 is cheaper at $1.25 / $4.25 per million input/output tokens, against $30 / $60 for GPT-4.
  • Muse Spark 1.3 accepts more context: 1.05M tokens versus 8K.

Side by side

GPT-4Muse Spark 1.3
ProviderOpenAIMeta
Noometry Index29.154.8
Released2023-03-142026-09-02
WeightsProprietaryProprietary
Context window8K1.05M
Max output8K131K
Input $ / M tokens$30$1.25
Output $ / M tokens$60$4.25
Results tracked3837

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

Category by category

Coding Muse Spark 1.3 leads

GPT-4: 31.6 (#283), Muse Spark 1.3: 56.6 (#21)

BenchmarkGPT-4Muse Spark 1.3
LMArena Coding12541514
CursorBench—41.6%
LMArena WebDev—1657
SciCode—59.7%
WeirdML12.4%—
BigCodeBench Instruct46%—
BigCodeBench Complete57.2%—
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, Muse Spark 1.3: 38.6 (#30)

BenchmarkGPT-4Muse Spark 1.3
APEX-Agents—57.8%
GDP.pdf—27.6%
METR Time Horizons36.1%—

Reasoning Muse Spark 1.3 leads

GPT-4: 17.8 (#289), Muse Spark 1.3: 54.0 (#27)

BenchmarkGPT-4Muse Spark 1.3
Chess Puzzles4%38%
LMArena Hard Prompts12411503
Mystery Game Puzzles12%25%
DTBench62.7%96.5%
LMCA17.1%53.9%
Epoch Capabilities Index125.89156.75
NYT Connections (extended)—85.1%
CritPt—26%
Bench to the Future 3—0.14
BIG-Bench Hard75.1%—
ForecastBench57.8—
HellaSwag95.3%—
WinoGrande87.5%—

Math Muse Spark 1.3 leads

GPT-4: 10.8 (#309), Muse Spark 1.3: 73.1 (#21)

BenchmarkGPT-4Muse Spark 1.3
OTIS Mock AIME 2024-20251.1%99.2%
LMArena Math12691494
FrontierMath (Tiers 1-3)—74.4%
FrontierMath Tier 4—46.3%
ProofBench—58%
MATH Level 523%—
GSM8K92%—

Knowledge Muse Spark 1.3 leads

GPT-4: 18.4 (#282), Muse Spark 1.3: 42.6 (#95)

BenchmarkGPT-4Muse Spark 1.3
LMArena Expert12111516
GPQA Diamond35.7%—
MMLU86.4%—
TriviaQA84.8%—

Multimodal Not comparable

GPT-4: —, Muse Spark 1.3: 43.7 (#22)

BenchmarkGPT-4Muse Spark 1.3
LMArena Vision—1309
LMArena Document—1471

Multilingual Muse Spark 1.3 leads

GPT-4: 40.6 (#215), Muse Spark 1.3: 57.4 (#8)

BenchmarkGPT-4Muse Spark 1.3
LMArena Non-English12461481
LMArena Chinese12421529
LMArena French12831524
LMArena German12511515
LMArena Japanese12091474
LMArena Korean11841501
LMArena Russian12511490
LMArena Spanish12611490

Instruction Following Muse Spark 1.3 leads

GPT-4: 65.3 (#222), Muse Spark 1.3: 77.5 (#22)

BenchmarkGPT-4Muse Spark 1.3
LMArena Instruction Following12411477

Long Context Muse Spark 1.3 leads

GPT-4: 37.7 (#212), Muse Spark 1.3: 45.6 (#32)

BenchmarkGPT-4Muse Spark 1.3
LMArena Longer Query12441488

Writing & Preference Muse Spark 1.3 leads

GPT-4: 34.9 (#268), Muse Spark 1.3: 73.6 (#9)

BenchmarkGPT-4Muse Spark 1.3
LMArena Text12631490
LMArena Creative Writing12441455
EQ-Bench Creative Writing7521906
LMArena Multi-Turn12571482

Frequently asked questions

Is GPT-4 better than Muse Spark 1.3?

Muse Spark 1.3 is the stronger model overall, scoring 54.8 to 29.1 on the Noometry Index.

Which is cheaper, GPT-4 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; GPT-4 lists at $30 and $60.

Is GPT-4 or Muse Spark 1.3 better for coding?

Muse Spark 1.3 scores higher on coding benchmarks: 56.6 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

Muse Spark 1.3 does, with 1.05M tokens against 8K.

How many benchmarks do GPT-4 and Muse Spark 1.3 share?

24 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Muse Spark 1.3 has 37.

Related comparisons

Go deeper