Noometry

Model comparison

GPT-4 Turbo vs Muse Spark 1.2

Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 30.5 on the Noometry Index.

Last verified . 20 shared benchmarks.

GPT-4 Turbo OpenAI

30.5

Rank #292 Confirmed

Muse Spark 1.2 Meta

50.3

Rank #48 Confirmed

Summary

  • They share 20 benchmarks with published results for both. GPT-4 Turbo 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 math, where Muse Spark 1.2 leads 46.4 to 9.0.
  • The biggest single-benchmark swing is SimpleBench: 25.1% for GPT-4 Turbo and 74.5% for Muse Spark 1.2.
  • Muse Spark 1.2 is cheaper at $1.25 / $4.25 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
  • Muse Spark 1.2 accepts more context: 1.05M tokens versus 128K.

Side by side

GPT-4 TurboMuse Spark 1.2
ProviderOpenAIMeta
Noometry Index30.550.3
Released2023-11-062026-08-05
WeightsProprietaryProprietary
Context window128K1.05M
Max output4K131K
Input $ / M tokens$10$1.25
Output $ / M tokens$30$4.25
Results tracked3631

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

Category by category

Coding Muse Spark 1.2 leads

GPT-4 Turbo: 33.8 (#249), Muse Spark 1.2: 49.2 (#51)

BenchmarkGPT-4 TurboMuse Spark 1.2
WeirdML18%60.3%
LMArena Coding12681495
DeepSWE—54.9%
LMArena WebDev—1533
FrontierSWE—12%
SciCode—56.4%
BigCodeBench Instruct48.2%—
BigCodeBench Complete58.2%—
HumanEval+86.6%—
MBPP+73.3%—

Agentic & Tool Use Not comparable

GPT-4 Turbo: —, Muse Spark 1.2: 29.4 (#87)

BenchmarkGPT-4 TurboMuse Spark 1.2
APEX-Agents—36.4%
GDP.pdf—16%
METR Time Horizons36.7%—

Reasoning Muse Spark 1.2 leads

GPT-4 Turbo: 15.3 (#317), Muse Spark 1.2: 51.3 (#34)

BenchmarkGPT-4 TurboMuse Spark 1.2
SimpleBench25.1%74.5%
LMArena Hard Prompts12511486
DTBench61.6%94.7%
LMCA9.8%48.4%
Epoch Capabilities Index127.25154.87
NYT Connections (extended)—79.2%
CritPt—17.7%
Chess Puzzles6%—
ForecastBench59.4—

Math Muse Spark 1.2 leads

GPT-4 Turbo: 9.0 (#322), Muse Spark 1.2: 46.4 (#70)

BenchmarkGPT-4 TurboMuse Spark 1.2
LMArena Math12721471
FrontierMath (Tiers 1-3)0.7%—
OTIS Mock AIME 2024-20256.7%—
ProofBench—43%
MATH Level 546.7%—

Knowledge Muse Spark 1.2 leads

GPT-4 Turbo: 24.3 (#268), Muse Spark 1.2: 54.1 (#53)

BenchmarkGPT-4 TurboMuse Spark 1.2
LMArena Expert12231480
GPQA Diamond46.6%—
SimpleQA Verified—60.3%
Confabulations28.4%—
MMLU81.3%—

Multimodal Muse Spark 1.2 leads

GPT-4 Turbo: 30.6 (#110), Muse Spark 1.2: 43.4 (#25)

BenchmarkGPT-4 TurboMuse Spark 1.2
LMArena Vision10901305

Multilingual Muse Spark 1.2 leads

GPT-4 Turbo: 40.5 (#216), Muse Spark 1.2: 57.1 (#11)

BenchmarkGPT-4 TurboMuse Spark 1.2
LMArena Non-English12451478
LMArena Chinese12421511
LMArena French12761513
LMArena Russian12591487
LMArena Spanish12601498
LMArena German1259—
LMArena Japanese1194—
LMArena Korean1187—

Instruction Following Muse Spark 1.2 leads

GPT-4 Turbo: 65.8 (#216), Muse Spark 1.2: 76.7 (#36)

BenchmarkGPT-4 TurboMuse Spark 1.2
LMArena Instruction Following12491461

Long Context Muse Spark 1.2 leads

GPT-4 Turbo: 38.0 (#206), Muse Spark 1.2: 45.2 (#48)

BenchmarkGPT-4 TurboMuse Spark 1.2
LMArena Longer Query12541475

Writing & Preference Muse Spark 1.2 leads

GPT-4 Turbo: 47.7 (#206), Muse Spark 1.2: 72.3 (#14)

BenchmarkGPT-4 TurboMuse Spark 1.2
LMArena Text12721482
LMArena Creative Writing12691449
LMArena Multi-Turn12671494
EQ-Bench Creative Writing—1840

Frequently asked questions

Is GPT-4 Turbo better than Muse Spark 1.2?

Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 30.5 on the Noometry Index.

Which is cheaper, GPT-4 Turbo 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 Turbo lists at $10 and $30.

Is GPT-4 Turbo or Muse Spark 1.2 better for coding?

Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 33.8 in the Noometry coding category.

Which has the bigger context window?

Muse Spark 1.2 does, with 1.05M tokens against 128K.

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

20 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Muse Spark 1.2 has 31.

Related comparisons

Go deeper