Noometry

Model comparison

GPT-4 vs Muse Spark 1.2

Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 29.1 on the Noometry Index.

Last verified . 19 shared benchmarks.

GPT-4 OpenAI

29.1

Rank #316 Confirmed

Muse Spark 1.2 Meta

50.3

Rank #48 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GPT-4 scores higher in 0 categories and Muse Spark 1.2 in 8 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Muse Spark 1.2 leads 72.3 to 34.9.
  • The biggest single-benchmark swing is WeirdML: 12.4% for GPT-4 and 60.3% for Muse Spark 1.2.
  • Muse Spark 1.2 is cheaper at $1.25 / $4.25 per million input/output tokens, against $30 / $60 for GPT-4.
  • Muse Spark 1.2 accepts more context: 1.05M tokens versus 8K.

Side by side

GPT-4Muse Spark 1.2
ProviderOpenAIMeta
Noometry Index29.150.3
Released2023-03-142026-08-05
WeightsProprietaryProprietary
Context window8K1.05M
Max output8K131K
Input $ / M tokens$30$1.25
Output $ / M tokens$60$4.25
Results tracked3831

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

Category by category

Coding Muse Spark 1.2 leads

GPT-4: 31.6 (#283), Muse Spark 1.2: 49.2 (#51)

BenchmarkGPT-4Muse Spark 1.2
WeirdML12.4%60.3%
LMArena Coding12541495
DeepSWE—54.9%
LMArena WebDev—1533
FrontierSWE—12%
SciCode—56.4%
BigCodeBench Instruct46%—
BigCodeBench Complete57.2%—
HumanEval+79.3%—

Agentic & Tool Use Not comparable

GPT-4: —, Muse Spark 1.2: 29.4 (#87)

BenchmarkGPT-4Muse Spark 1.2
APEX-Agents—36.4%
GDP.pdf—16%
METR Time Horizons36.1%—

Reasoning Muse Spark 1.2 leads

GPT-4: 17.8 (#289), Muse Spark 1.2: 51.3 (#34)

BenchmarkGPT-4Muse Spark 1.2
LMArena Hard Prompts12411486
DTBench62.7%94.7%
LMCA17.1%48.4%
Epoch Capabilities Index125.89154.87
SimpleBench—74.5%
NYT Connections (extended)—79.2%
CritPt—17.7%
Chess Puzzles4%—
Mystery Game Puzzles12%—
BIG-Bench Hard75.1%—
ForecastBench57.8—
HellaSwag95.3%—
WinoGrande87.5%—

Math Muse Spark 1.2 leads

GPT-4: 10.8 (#309), Muse Spark 1.2: 46.4 (#70)

BenchmarkGPT-4Muse Spark 1.2
LMArena Math12691471
OTIS Mock AIME 2024-20251.1%—
ProofBench—43%
MATH Level 523%—
GSM8K92%—

Knowledge Muse Spark 1.2 leads

GPT-4: 18.4 (#282), Muse Spark 1.2: 54.1 (#53)

BenchmarkGPT-4Muse Spark 1.2
LMArena Expert12111480
GPQA Diamond35.7%—
SimpleQA Verified—60.3%
MMLU86.4%—
TriviaQA84.8%—

Multimodal Not comparable

GPT-4: —, Muse Spark 1.2: 43.4 (#25)

BenchmarkGPT-4Muse Spark 1.2
LMArena Vision—1305

Multilingual Muse Spark 1.2 leads

GPT-4: 40.6 (#215), Muse Spark 1.2: 57.1 (#11)

BenchmarkGPT-4Muse Spark 1.2
LMArena Non-English12461478
LMArena Chinese12421511
LMArena French12831513
LMArena Russian12511487
LMArena Spanish12611498
LMArena German1251—
LMArena Japanese1209—
LMArena Korean1184—

Instruction Following Muse Spark 1.2 leads

GPT-4: 65.3 (#222), Muse Spark 1.2: 76.7 (#36)

BenchmarkGPT-4Muse Spark 1.2
LMArena Instruction Following12411461

Long Context Muse Spark 1.2 leads

GPT-4: 37.7 (#212), Muse Spark 1.2: 45.2 (#48)

BenchmarkGPT-4Muse Spark 1.2
LMArena Longer Query12441475

Writing & Preference Muse Spark 1.2 leads

GPT-4: 34.9 (#268), Muse Spark 1.2: 72.3 (#14)

BenchmarkGPT-4Muse Spark 1.2
LMArena Text12631482
LMArena Creative Writing12441449
EQ-Bench Creative Writing7521840
LMArena Multi-Turn12571494

Frequently asked questions

Is GPT-4 better than Muse Spark 1.2?

Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 29.1 on the Noometry Index.

Which is cheaper, GPT-4 or Muse Spark 1.2?

Muse Spark 1.2 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 1.2 better for coding?

Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 31.6 in the Noometry coding category.

Which has the bigger context window?

Muse Spark 1.2 does, with 1.05M tokens against 8K.

How many benchmarks do GPT-4 and Muse Spark 1.2 share?

19 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Muse Spark 1.2 has 31.

Related comparisons

Go deeper