Noometry

Model comparison

Claude Haiku 4.5 vs Muse Spark

Muse Spark is the stronger model overall, scoring 50.6 to 39.5 on the Noometry Index.

Last verified . 24 shared benchmarks.

Claude Haiku 4.5 Anthropic

39.5

Rank #165 Confirmed

Muse Spark Meta

50.6

Rank #46 Confirmed

Summary

  • They share 24 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 0 categories and Muse Spark in 9 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Muse Spark leads 65.7 to 37.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 66.7% for Claude Haiku 4.5 and 88.9% for Muse Spark.

Side by side

Claude Haiku 4.5Muse Spark
ProviderAnthropicMeta
Noometry Index39.550.6
Released2025-10-152026-04-08
WeightsProprietaryProprietary
Context window200K—
Max output64K—
Input $ / M tokens$1—
Output $ / M tokens$5—
Results tracked5327

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

Category by category

Coding Muse Spark leads

Claude Haiku 4.5: 44.0 (#78), Muse Spark: 46.2 (#69)

BenchmarkClaude Haiku 4.5Muse Spark
SciCode43.3%51.5%
LMArena Coding14531481
SWE-bench Verified (bash only)66.6%—
LMArena WebDev1330—
SWE-bench Multilingual64.7%—
WeirdML45.4%—
ALE-Bench653.48—

Agentic & Tool Use Not comparable

Claude Haiku 4.5: 33.6 (#52), Muse Spark: —

BenchmarkClaude Haiku 4.5Muse Spark
Terminal-Bench35.5%—
Berkeley Function Calling Leaderboard68.7%—
DeepResearch Bench45.5%—
BALROG31.2%—
ExploitBench13.7%—
Vending-Bench 2458.89—

Reasoning Muse Spark leads

Claude Haiku 4.5: 15.1 (#320), Muse Spark: 35.9 (#67)

BenchmarkClaude Haiku 4.5Muse Spark
CritPt0%11.3%
LMArena Hard Prompts14201474
Epoch Capabilities Index142.41152.04
ARC-AGI-24%—
NYT Connections (extended)14.3%—
ARC-AGI-147.7%—
Chess Puzzles8%—
DTBench73.6%—
LMCA30.9%—
ForecastBench61.4—

Math Muse Spark leads

Claude Haiku 4.5: 44.9 (#78), Muse Spark: 47.8 (#66)

BenchmarkClaude Haiku 4.5Muse Spark
OTIS Mock AIME 2024-202566.7%88.9%
LMArena Math13961455
FrontierMath (Feb 2025 set)5.9%39%
FrontierMath Tier 4 (v1)2.1%14.6%
ProofBench—17%
Omni-MATH56.1%—
MATH Level 596.4%—

Knowledge Muse Spark leads

Claude Haiku 4.5: 37.7 (#153), Muse Spark: 65.7 (#13)

BenchmarkClaude Haiku 4.5Muse Spark
GPQA Diamond71.2%89.8%
LMArena Expert14421457
Humanity's Last Exam—40.6%
SimpleQA Verified13.2%—
MMLU-Pro77.7%—
Vectara Hallucination Rate9.8%—
GPQA (HELM)60.5%—

Multimodal Muse Spark leads

Claude Haiku 4.5: 26.8 (#118), Muse Spark: 43.4 (#24)

BenchmarkClaude Haiku 4.5Muse Spark
LMArena Document14201444
LMArena Vision—1306
Blueprint-Bench 20%—

Multilingual Muse Spark leads

Claude Haiku 4.5: 49.9 (#129), Muse Spark: 56.1 (#24)

BenchmarkClaude Haiku 4.5Muse Spark
LMArena Non-English13771464
LMArena Chinese14171509
LMArena French14081497
LMArena German13751497
LMArena Korean13471459
LMArena Russian13811466
LMArena Spanish14201472
LMArena Japanese1339—

Instruction Following Muse Spark leads

Claude Haiku 4.5: 71.4 (#149), Muse Spark: 75.9 (#51)

BenchmarkClaude Haiku 4.5Muse Spark
LMArena Instruction Following14141442
IFEval80.1%—

Long Context Too close to call

Claude Haiku 4.5: 43.6 (#92), Muse Spark: 44.4 (#69)

BenchmarkClaude Haiku 4.5Muse Spark
LMArena Longer Query14271451

Writing & Preference Muse Spark leads

Claude Haiku 4.5: 57.9 (#123), Muse Spark: 66.0 (#39)

BenchmarkClaude Haiku 4.5Muse Spark
LMArena Text13961474
LMArena Creative Writing13721459
LMArena Multi-Turn14091477
WildBench83.9%—
EQ-Bench 41064—

Frequently asked questions

Is Claude Haiku 4.5 better than Muse Spark?

Muse Spark is the stronger model overall, scoring 50.6 to 39.5 on the Noometry Index.

Is Claude Haiku 4.5 or Muse Spark better for coding?

Muse Spark scores higher on coding benchmarks: 46.2 versus 44.0 in the Noometry coding category.

How many benchmarks do Claude Haiku 4.5 and Muse Spark share?

24 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Muse Spark has 27.

Related comparisons

Go deeper