Noometry

Model comparison

GPT-5.4 vs Muse Spark

GPT-5.4 is the stronger model overall, scoring 59.4 to 50.6 on the Noometry Index.

Last verified . 27 shared benchmarks.

GPT-5.4 OpenAI

59.4

Rank #16 Confirmed

Muse Spark Meta

50.6

Rank #46 Confirmed

Summary

  • They share 27 benchmarks with published results for both. GPT-5.4 scores higher in 8 categories and Muse Spark in 1 category; 6 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GPT-5.4 leads 61.8 to 35.9.
  • The biggest single-benchmark swing is ProofBench: 56% for GPT-5.4 and 17% for Muse Spark.

Side by side

GPT-5.4Muse Spark
ProviderOpenAIMeta
Noometry Index59.450.6
Released2026-03-052026-04-08
WeightsProprietaryProprietary
Context window1.05M—
Max output128K—
Input $ / M tokens$2.50—
Output $ / M tokens$15—
Results tracked6827

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

Category by category

Coding GPT-5.4 leads

GPT-5.4: 52.6 (#33), Muse Spark: 46.2 (#69)

BenchmarkGPT-5.4Muse Spark
SciCode56.6%51.5%
LMArena Coding14971481
SWE-bench Verified76.9%—
DeepSWE51.8%—
LMArena WebDev1465—
GSO31.4%—
WeirdML77.7%—
MirrorCode15.6%—
ALE-Bench1,607—
AlgoTune1.85—

Agentic & Tool Use Not comparable

GPT-5.4: 46.5 (#13), Muse Spark: —

BenchmarkGPT-5.4Muse Spark
Terminal-Bench81.8%—
APEX-Agents52.4%—
τ²-bench Banking39.4%—
DeepResearch Bench35.1%—
PostTrainBench19%—
GBAEval45.1%—
LMArena Search1197—
METR Time Horizons74.3%—
Vending-Bench 26,144—

Reasoning GPT-5.4 leads

GPT-5.4: 61.8 (#19), Muse Spark: 35.9 (#67)

BenchmarkGPT-5.4Muse Spark
CritPt23.4%11.3%
LMArena Hard Prompts14851474
Epoch Capabilities Index156.81152.04
ARC-AGI-274%—
Kagi LLM Benchmark63.8%—
NYT Connections (extended)91.3%—
ARC-AGI-193.7%—
Chess Puzzles44%—
EnigmaEval16%—
Thematic Generalization80%—
EBR-Bench25.4%—
Mystery Game Puzzles37%—
DTBench94.4%—
LMCA52%—
ForecastBench59.5—

Math GPT-5.4 leads

GPT-5.4: 73.5 (#19), Muse Spark: 47.8 (#66)

BenchmarkGPT-5.4Muse Spark
OTIS Mock AIME 2024-202597.8%88.9%
ProofBench56%17%
LMArena Math14881455
FrontierMath (Feb 2025 set)47.6%39%
FrontierMath Tier 4 (v1)27.1%14.6%
FrontierMath (Tiers 1-3)78.6%—
FrontierMath Tier 449%—
MathArena Final-Answer Competitions83.1%—

Knowledge Too close to call

GPT-5.4: 65.3 (#14), Muse Spark: 65.7 (#13)

BenchmarkGPT-5.4Muse Spark
GPQA Diamond93.3%89.8%
Humanity's Last Exam36.2%40.6%
LMArena Expert15071457
SimpleQA Verified45.1%—
Vectara Hallucination Rate7%—

Multimodal Too close to call

GPT-5.4: 43.7 (#20), Muse Spark: 43.4 (#24)

BenchmarkGPT-5.4Muse Spark
LMArena Vision13031306
LMArena Document14711444
Blueprint-Bench 227.1%—
Furniture Assembly37.5%—

Multilingual Too close to call

GPT-5.4: 56.2 (#23), Muse Spark: 56.1 (#24)

BenchmarkGPT-5.4Muse Spark
LMArena Non-English14651464
LMArena Chinese15191509
LMArena French14931497
LMArena German14721497
LMArena Korean14481459
LMArena Russian14801466
LMArena Spanish14541472
LMArena Japanese1485—

Instruction Following GPT-5.4 leads

GPT-5.4: 77.1 (#27), Muse Spark: 75.9 (#51)

BenchmarkGPT-5.4Muse Spark
LMArena Instruction Following14691442

Long Context GPT-5.4 leads

GPT-5.4: 50.3 (#8), Muse Spark: 44.4 (#69)

BenchmarkGPT-5.4Muse Spark
LMArena Longer Query14731451
CL-bench27.9%—
CL-bench Life21.7%—

Writing & Preference GPT-5.4 leads

GPT-5.4: 71.9 (#17), Muse Spark: 66.0 (#39)

BenchmarkGPT-5.4Muse Spark
LMArena Text14691474
LMArena Creative Writing14391459
LMArena Multi-Turn14821477
EQ-Bench Creative Writing1840—
EQ-Bench 41272—

Frequently asked questions

Is GPT-5.4 better than Muse Spark?

GPT-5.4 is the stronger model overall, scoring 59.4 to 50.6 on the Noometry Index.

Is GPT-5.4 or Muse Spark better for coding?

GPT-5.4 scores higher on coding benchmarks: 52.6 versus 46.2 in the Noometry coding category.

How many benchmarks do GPT-5.4 and Muse Spark share?

27 benchmarks have published results for both models. GPT-5.4 has 68 scored results on Noometry and Muse Spark has 27.

Related comparisons

Go deeper