Noometry

Model comparison

Claude 3 Haiku vs Muse Spark 1.1

Muse Spark 1.1 is the stronger model overall, scoring 49.9 to 25.9 on the Noometry Index.

Last verified . 22 shared benchmarks.

Claude 3 Haiku Anthropic

25.9

Rank #340 Confirmed

Muse Spark 1.1 Meta

49.9

Rank #51 Confirmed

Summary

  • They share 22 benchmarks with published results for both. Claude 3 Haiku scores higher in 0 categories and Muse Spark 1.1 in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Muse Spark 1.1 leads 73.4 to 29.7.
  • The biggest single-benchmark swing is DTBench: 50.1% for Claude 3 Haiku and 94.4% for Muse Spark 1.1.

Side by side

Claude 3 HaikuMuse Spark 1.1
ProviderAnthropicMeta
Noometry Index25.949.9
Released2024-03-072026-04-08
WeightsProprietaryProprietary
Context window—1.05M
Max output—131K
Input $ / M tokens—$1.25
Output $ / M tokens—$4.25
Results tracked3737

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

Category by category

Coding Muse Spark 1.1 leads

Claude 3 Haiku: 26.4 (#325), Muse Spark 1.1: 51.3 (#40)

BenchmarkClaude 3 HaikuMuse Spark 1.1
LMArena Coding11991498
DeepSWE—53.3%
LMArena WebDev—1542
SciCode—58.8%
WeirdML9.8%—
BigCodeBench Instruct39.4%—
BigCodeBench Complete50.1%—
CadEval12%—
HumanEval+68.9%—
MBPP+68.8%—

Agentic & Tool Use Not comparable

Claude 3 Haiku: —, Muse Spark 1.1: 30.8 (#73)

BenchmarkClaude 3 HaikuMuse Spark 1.1
APEX-Agents—31.8%
τ²-bench Banking—40.5%
GBAEval—7.9%
GDP.pdf—15%
Vending-Bench 2—6,520

Reasoning Muse Spark 1.1 leads

Claude 3 Haiku: 16.3 (#307), Muse Spark 1.1: 47.1 (#44)

BenchmarkClaude 3 HaikuMuse Spark 1.1
LMArena Hard Prompts11741486
DTBench50.1%94.4%
LMCA8.8%49.9%
Epoch Capabilities Index118.35154.21
Kagi LLM Benchmark34.2%—
NYT Connections (extended)—84.9%
CritPt—15.1%
Surface Evolver Bench—52.5%
ForecastBench53.2—
WinoGrande74.2%—

Math Muse Spark 1.1 leads

Claude 3 Haiku: 9.8 (#319), Muse Spark 1.1: 45.5 (#76)

BenchmarkClaude 3 HaikuMuse Spark 1.1
LMArena Math11881483
OTIS Mock AIME 2024-20251.8%—
ProofBench—39%
MATH Level 514.9%—

Knowledge Muse Spark 1.1 leads

Claude 3 Haiku: 17.3 (#285), Muse Spark 1.1: 53.1 (#59)

BenchmarkClaude 3 HaikuMuse Spark 1.1
LMArena Expert11481478
GPQA Diamond36.3%—
SimpleQA Verified—57.8%
Confabulations34.2%—
MMLU73.8%—

Multimodal Muse Spark 1.1 leads

Claude 3 Haiku: 23.6 (#128), Muse Spark 1.1: 42.6 (#29)

BenchmarkClaude 3 HaikuMuse Spark 1.1
LMArena Vision9501293
LMArena Document—1465
ScienceQA72%—

Multilingual Muse Spark 1.1 leads

Claude 3 Haiku: 36.0 (#243), Muse Spark 1.1: 56.7 (#17)

BenchmarkClaude 3 HaikuMuse Spark 1.1
LMArena Non-English11781472
LMArena Chinese11551518
LMArena French11951494
LMArena German11741466
LMArena Japanese11021451
LMArena Korean11091458
LMArena Russian12041483
LMArena Spanish11661464

Instruction Following Muse Spark 1.1 leads

Claude 3 Haiku: 61.3 (#247), Muse Spark 1.1: 76.5 (#39)

BenchmarkClaude 3 HaikuMuse Spark 1.1
LMArena Instruction Following11731457

Long Context Muse Spark 1.1 leads

Claude 3 Haiku: 36.1 (#237), Muse Spark 1.1: 44.8 (#58)

BenchmarkClaude 3 HaikuMuse Spark 1.1
LMArena Longer Query11901462

Writing & Preference Muse Spark 1.1 leads

Claude 3 Haiku: 29.7 (#291), Muse Spark 1.1: 73.4 (#11)

BenchmarkClaude 3 HaikuMuse Spark 1.1
LMArena Text11951479
LMArena Creative Writing11571437
EQ-Bench Creative Writing7171927
LMArena Multi-Turn11901485
EQ-Bench 4—1260

Frequently asked questions

Is Claude 3 Haiku better than Muse Spark 1.1?

Muse Spark 1.1 is the stronger model overall, scoring 49.9 to 25.9 on the Noometry Index.

Is Claude 3 Haiku or Muse Spark 1.1 better for coding?

Muse Spark 1.1 scores higher on coding benchmarks: 51.3 versus 26.4 in the Noometry coding category.

How many benchmarks do Claude 3 Haiku and Muse Spark 1.1 share?

22 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Muse Spark 1.1 has 37.

Related comparisons

Go deeper