Noometry

Model comparison

Claude 3.5 Haiku vs Step 5 Preview

Step 5 Preview is the stronger model overall, scoring 47.9 to 29.2 on the Noometry Index.

Last verified . 16 shared benchmarks.

Claude 3.5 Haiku Anthropic

29.2

Rank #315 Confirmed

Step 5 Preview StepFun

47.9

Rank #58 Confirmed

Summary

  • They share 16 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 0 categories and Step 5 Preview in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Step 5 Preview leads 46.1 to 14.7.
  • The biggest single-benchmark swing is SciCode: 27.4% for Claude 3.5 Haiku and 58.9% for Step 5 Preview.

Side by side

Claude 3.5 HaikuStep 5 Preview
ProviderAnthropicStepFun
Noometry Index29.247.9
Released2024-10-222026-09-16
WeightsProprietaryProprietary
Context window—1.02M
Max output—66K
Input $ / M tokens—$1
Output $ / M tokens—$2.70
Results tracked4918

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

Category by category

Coding Step 5 Preview leads

Claude 3.5 Haiku: 32.9 (#265), Step 5 Preview: 51.8 (#36)

BenchmarkClaude 3.5 HaikuStep 5 Preview
SciCode27.4%58.9%
LMArena Coding12861480
Aider Polyglot28%—
LMArena WebDev—1564
WeirdML30.7%—
BigCodeBench Instruct46.1%—
LiveBench Coding51.4%—
BigCodeBench Complete59%—
CadEval32%—

Agentic & Tool Use Not comparable

Claude 3.5 Haiku: 28.0 (#95), Step 5 Preview: —

BenchmarkClaude 3.5 HaikuStep 5 Preview
BALROG19.3%—

Reasoning Step 5 Preview leads

Claude 3.5 Haiku: 17.7 (#290), Step 5 Preview: 40.0 (#57)

BenchmarkClaude 3.5 HaikuStep 5 Preview
CritPt0%20.9%
LMArena Hard Prompts12511465
LiveBench Reasoning28.1%—
DTBench56.7%—
LiveBench Data Analysis48.5%—
Epoch Capabilities Index127.15—
LiveBench43.5%—

Math Step 5 Preview leads

Claude 3.5 Haiku: 14.7 (#300), Step 5 Preview: 46.1 (#72)

BenchmarkClaude 3.5 HaikuStep 5 Preview
LMArena Math12441470
OTIS Mock AIME 2024-20254.3%—
ProofBench—42%
Omni-MATH22.4%—
LiveBench Math35.5%—
MATH Level 546.4%—
FrontierMath (Feb 2025 set)0.3%—

Knowledge Step 5 Preview leads

Claude 3.5 Haiku: 18.7 (#281), Step 5 Preview: 41.2 (#112)

BenchmarkClaude 3.5 HaikuStep 5 Preview
LMArena Expert12081470
GPQA Diamond38.1%—
MMLU-Pro60.5%—
Confabulations36.7%—
GPQA (HELM)36.3%—
MMLU74.3%—

Multimodal Step 5 Preview leads

Claude 3.5 Haiku: 26.8 (#117), Step 5 Preview: 41.0 (#41)

BenchmarkClaude 3.5 HaikuStep 5 Preview
LMArena Vision10921267
GeoBench34%—

Multilingual Step 5 Preview leads

Claude 3.5 Haiku: 40.0 (#218), Step 5 Preview: 53.8 (#54)

BenchmarkClaude 3.5 HaikuStep 5 Preview
LMArena Non-English12381432
LMArena Chinese12291519
LMArena Russian12531436
LMArena Spanish12611439
LMArena French1264—
LMArena German1237—
LMArena Japanese1175—
LMArena Korean1173—

Instruction Following Step 5 Preview leads

Claude 3.5 Haiku: 62.9 (#234), Step 5 Preview: 76.0 (#50)

BenchmarkClaude 3.5 HaikuStep 5 Preview
LMArena Instruction Following12411444
LiveBench Instruction Following61.9%—
IFEval79.2%—

Long Context Step 5 Preview leads

Claude 3.5 Haiku: 38.3 (#200), Step 5 Preview: 44.5 (#64)

BenchmarkClaude 3.5 HaikuStep 5 Preview
LMArena Longer Query12611455

Writing & Preference Step 5 Preview leads

Claude 3.5 Haiku: 42.7 (#234), Step 5 Preview: 62.8 (#71)

BenchmarkClaude 3.5 HaikuStep 5 Preview
LMArena Text12551442
LMArena Creative Writing12331410
LMArena Multi-Turn12651447
Short-Story Creative Writing73.5%—
EQ-Bench Creative Writing1146—
WildBench76%—
LiveBench Language35.4%—

Frequently asked questions

Is Claude 3.5 Haiku better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 29.2 on the Noometry Index.

Is Claude 3.5 Haiku or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 32.9 in the Noometry coding category.

How many benchmarks do Claude 3.5 Haiku and Step 5 Preview share?

16 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Step 5 Preview has 18.

Related comparisons

Go deeper