Noometry

Model comparison

Claude Sonnet 5 vs Step 3

Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 40.5 on the Noometry Index.

Last verified . 16 shared benchmarks.

Claude Sonnet 5 Anthropic

54.6

Rank #29 Confirmed

Step 3 StepFun

40.5

Rank #149 Confirmed

Summary

  • They share 16 benchmarks with published results for both. Claude Sonnet 5 scores higher in 9 categories and Step 3 in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Sonnet 5 leads 66.2 to 37.6.
  • Step 3 has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 5Step 3
ProviderAnthropicStepFun
Noometry Index54.640.5
Released2026-06-29—
WeightsProprietaryOpen
Context window1M—
Max output128K—
Input $ / M tokens$2—
Output $ / M tokens$10—
Results tracked5117

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

Category by category

Coding Claude Sonnet 5 leads

Claude Sonnet 5: 55.5 (#26), Step 3: 40.1 (#147)

BenchmarkClaude Sonnet 5Step 3
LMArena Coding14831367
DeepSWE53.8%—
FrontierCode42.7%—
CursorBench34.1%—
LMArena WebDev1541—
SciCode54.3%—
GSO37.3%—
WeirdML68.8%—
ALE-Bench1,463—

Agentic & Tool Use Not comparable

Claude Sonnet 5: 42.8 (#18), Step 3: —

BenchmarkClaude Sonnet 5Step 3
APEX-Agents54.5%—
GBAEval65.3%—
LMArena Search1194—
Vending-Bench 26,378—

Reasoning Claude Sonnet 5 leads

Claude Sonnet 5: 49.1 (#39), Step 3: 28.4 (#105)

BenchmarkClaude Sonnet 5Step 3
LMArena Hard Prompts14611355
SimpleBench60.6%—
Kagi LLM Benchmark—62.3%
NYT Connections (extended)75.1%—
CritPt16.9%—
Chess Puzzles35%—
Mystery Game Puzzles35%—
DTBench92.5%—
LMCA50%—
Surface Evolver Bench60%—
Bench to the Future 30.14—
Epoch Capabilities Index156.21—
ForecastBench61.1—

Math Claude Sonnet 5 leads

Claude Sonnet 5: 66.2 (#27), Step 3: 37.6 (#148)

BenchmarkClaude Sonnet 5Step 3
LMArena Math14671366
FrontierMath (Tiers 1-3)65.6%—
FrontierMath Tier 429.3%—
OTIS Mock AIME 2024-202594.7%—
ProofBench77%—

Knowledge Claude Sonnet 5 leads

Claude Sonnet 5: 55.6 (#47), Step 3: 36.8 (#164)

BenchmarkClaude Sonnet 5Step 3
LMArena Expert14901333
GPQA Diamond90.5%—
SimpleQA Verified33.7%—

Multimodal Claude Sonnet 5 leads

Claude Sonnet 5: 42.4 (#31), Step 3: 35.5 (#86)

BenchmarkClaude Sonnet 5Step 3
LMArena Vision12741177
Blueprint-Bench 224.9%—
LMArena Document1466—

Multilingual Claude Sonnet 5 leads

Claude Sonnet 5: 53.8 (#55), Step 3: 46.3 (#159)

BenchmarkClaude Sonnet 5Step 3
LMArena Non-English14311327
LMArena Chinese14771397
LMArena German14401371
LMArena Korean14111269
LMArena Russian14511331
LMArena Spanish14371371
LMArena French1460—
LMArena Japanese1422—

Instruction Following Claude Sonnet 5 leads

Claude Sonnet 5: 76.3 (#41), Step 3: 70.4 (#164)

BenchmarkClaude Sonnet 5Step 3
LMArena Instruction Following14521332

Long Context Claude Sonnet 5 leads

Claude Sonnet 5: 44.8 (#55), Step 3: 40.3 (#157)

BenchmarkClaude Sonnet 5Step 3
LMArena Longer Query14631326

Writing & Preference Claude Sonnet 5 leads

Claude Sonnet 5: 69.2 (#25), Step 3: 54.3 (#151)

BenchmarkClaude Sonnet 5Step 3
LMArena Text14421350
LMArena Creative Writing14161321
LMArena Multi-Turn14541341
EQ-Bench Creative Writing1794—
EQ-Bench 41236—

Frequently asked questions

Is Claude Sonnet 5 better than Step 3?

Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 40.5 on the Noometry Index.

Is Claude Sonnet 5 or Step 3 better for coding?

Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 40.1 in the Noometry coding category.

How many benchmarks do Claude Sonnet 5 and Step 3 share?

16 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and Step 3 has 17.

Related comparisons

Go deeper