Noometry

Model comparison

Claude 3.5 Haiku vs Step 3

Step 3 is the stronger model overall, scoring 40.5 to 29.2 on the Noometry Index.

Last verified . 16 shared benchmarks.

Claude 3.5 Haiku Anthropic

29.2

Rank #315 Confirmed

Step 3 StepFun

40.5

Rank #149 Confirmed

Summary

  • They share 16 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 0 categories and Step 3 in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Step 3 leads 37.6 to 14.7.
  • Step 3 has downloadable open weights; the other is API-only.

Side by side

Claude 3.5 HaikuStep 3
ProviderAnthropicStepFun
Noometry Index29.240.5
Released2024-10-22—
WeightsProprietaryOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked4917

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

Category by category

Coding Step 3 leads

Claude 3.5 Haiku: 32.9 (#265), Step 3: 40.1 (#147)

BenchmarkClaude 3.5 HaikuStep 3
LMArena Coding12861367
Aider Polyglot28%—
SciCode27.4%—
WeirdML30.7%—
BigCodeBench Instruct46.1%—
LiveBench Coding51.4%—
BigCodeBench Complete59%—
CadEval32%—

Agentic & Tool Use Not comparable

Claude 3.5 Haiku: 28.0 (#95), Step 3: —

BenchmarkClaude 3.5 HaikuStep 3
BALROG19.3%—

Reasoning Step 3 leads

Claude 3.5 Haiku: 17.7 (#290), Step 3: 28.4 (#105)

BenchmarkClaude 3.5 HaikuStep 3
LMArena Hard Prompts12511355
Kagi LLM Benchmark—62.3%
CritPt0%—
LiveBench Reasoning28.1%—
DTBench56.7%—
LiveBench Data Analysis48.5%—
Epoch Capabilities Index127.15—
LiveBench43.5%—

Math Step 3 leads

Claude 3.5 Haiku: 14.7 (#300), Step 3: 37.6 (#148)

BenchmarkClaude 3.5 HaikuStep 3
LMArena Math12441366
OTIS Mock AIME 2024-20254.3%—
Omni-MATH22.4%—
LiveBench Math35.5%—
MATH Level 546.4%—
FrontierMath (Feb 2025 set)0.3%—

Knowledge Step 3 leads

Claude 3.5 Haiku: 18.7 (#281), Step 3: 36.8 (#164)

BenchmarkClaude 3.5 HaikuStep 3
LMArena Expert12081333
GPQA Diamond38.1%—
MMLU-Pro60.5%—
Confabulations36.7%—
GPQA (HELM)36.3%—
MMLU74.3%—

Multimodal Step 3 leads

Claude 3.5 Haiku: 26.8 (#117), Step 3: 35.5 (#86)

BenchmarkClaude 3.5 HaikuStep 3
LMArena Vision10921177
GeoBench34%—

Multilingual Step 3 leads

Claude 3.5 Haiku: 40.0 (#218), Step 3: 46.3 (#159)

BenchmarkClaude 3.5 HaikuStep 3
LMArena Non-English12381327
LMArena Chinese12291397
LMArena German12371371
LMArena Korean11731269
LMArena Russian12531331
LMArena Spanish12611371
LMArena French1264—
LMArena Japanese1175—

Instruction Following Step 3 leads

Claude 3.5 Haiku: 62.9 (#234), Step 3: 70.4 (#164)

BenchmarkClaude 3.5 HaikuStep 3
LMArena Instruction Following12411332
LiveBench Instruction Following61.9%—
IFEval79.2%—

Long Context Step 3 leads

Claude 3.5 Haiku: 38.3 (#200), Step 3: 40.3 (#157)

BenchmarkClaude 3.5 HaikuStep 3
LMArena Longer Query12611326

Writing & Preference Step 3 leads

Claude 3.5 Haiku: 42.7 (#234), Step 3: 54.3 (#151)

BenchmarkClaude 3.5 HaikuStep 3
LMArena Text12551350
LMArena Creative Writing12331321
LMArena Multi-Turn12651341
Short-Story Creative Writing73.5%—
EQ-Bench Creative Writing1146—
WildBench76%—
LiveBench Language35.4%—

Frequently asked questions

Is Claude 3.5 Haiku better than Step 3?

Step 3 is the stronger model overall, scoring 40.5 to 29.2 on the Noometry Index.

Is Claude 3.5 Haiku or Step 3 better for coding?

Step 3 scores higher on coding benchmarks: 40.1 versus 32.9 in the Noometry coding category.

How many benchmarks do Claude 3.5 Haiku and Step 3 share?

16 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Step 3 has 17.

Related comparisons

Go deeper