Noometry

Model comparison

Claude Sonnet 4.6 vs Step 3

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 40.5 on the Noometry Index.

Last verified . 16 shared benchmarks.

Claude Sonnet 4.6 Anthropic

50.3

Rank #50 Confirmed

Step 3 StepFun

40.5

Rank #149 Confirmed

Summary

  • They share 16 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 9 categories and Step 3 in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Sonnet 4.6 leads 46.1 to 28.4.
  • Step 3 has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 4.6Step 3
ProviderAnthropicStepFun
Noometry Index50.340.5
Released2026-02-17—
WeightsProprietaryOpen
Context window1M—
Max output128K—
Input $ / M tokens$3—
Output $ / M tokens$15—
Results tracked5717

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

Category by category

Coding Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 46.3 (#67), Step 3: 40.1 (#147)

BenchmarkClaude Sonnet 4.6Step 3
LMArena Coding15041367
SWE-bench Verified75.2%—
DeepSWE29.9%—
FrontierCode24.3%—
LMArena WebDev1522—
SciCode46.8%—
WeirdML66.1%—
ALE-Bench1,327—

Agentic & Tool Use Not comparable

Claude Sonnet 4.6: 39.1 (#28), Step 3: —

BenchmarkClaude Sonnet 4.6Step 3
Terminal-Bench53.4%—
APEX-Agents43%—
OSWorld 2.09.3%—
DeepResearch Bench54.9%—
OSWorld72.1%—
ExploitBench23.6%—
GBAEval48.8%—
GDP.pdf18%—
LMArena Search1221—
Vending-Bench 27,204—

Reasoning Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 46.1 (#45), Step 3: 28.4 (#105)

BenchmarkClaude Sonnet 4.6Step 3
LMArena Hard Prompts14841355
ARC-AGI-260.4%—
Kagi LLM Benchmark—62.3%
NYT Connections (extended)80.9%—
ARC-AGI-186.5%—
CritPt3.1%—
Chess Puzzles13%—
Thematic Generalization76.3%—
Mystery Game Puzzles16%—
DTBench89.9%—
LMCA46.5%—
Epoch Capabilities Index152.24—
ForecastBench62—

Math Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 52.9 (#49), Step 3: 37.6 (#148)

BenchmarkClaude Sonnet 4.6Step 3
LMArena Math14621366
OTIS Mock AIME 2024-202585.8%—
ProofBench45%—
FrontierMath (Feb 2025 set)32.4%—
FrontierMath Tier 4 (v1)8.3%—

Knowledge Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 51.7 (#65), Step 3: 36.8 (#164)

BenchmarkClaude Sonnet 4.6Step 3
LMArena Expert15001333
GPQA Diamond87.4%—
SimpleQA Verified35.5%—
Vectara Hallucination Rate10.6%—

Multimodal Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 38.0 (#68), Step 3: 35.5 (#86)

BenchmarkClaude Sonnet 4.6Step 3
LMArena Vision12831177
Blueprint-Bench 26.7%—
LMArena Document1482—

Multilingual Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 54.4 (#41), Step 3: 46.3 (#159)

BenchmarkClaude Sonnet 4.6Step 3
LMArena Non-English14401327
LMArena Chinese14911397
LMArena German14281371
LMArena Korean14111269
LMArena Russian14401331
LMArena Spanish14641371
LMArena French1465—
LMArena Japanese1420—

Instruction Following Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 77.4 (#25), Step 3: 70.4 (#164)

BenchmarkClaude Sonnet 4.6Step 3
LMArena Instruction Following14751332

Long Context Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 45.3 (#44), Step 3: 40.3 (#157)

BenchmarkClaude Sonnet 4.6Step 3
LMArena Longer Query14791326

Writing & Preference Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 70.2 (#22), Step 3: 54.3 (#151)

BenchmarkClaude Sonnet 4.6Step 3
LMArena Text14581350
LMArena Creative Writing14351321
LMArena Multi-Turn14641341
EQ-Bench Creative Writing1810—
EQ-Bench 41207—

Frequently asked questions

Is Claude Sonnet 4.6 better than Step 3?

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 40.5 on the Noometry Index.

Is Claude Sonnet 4.6 or Step 3 better for coding?

Claude Sonnet 4.6 scores higher on coding benchmarks: 46.3 versus 40.1 in the Noometry coding category.

How many benchmarks do Claude Sonnet 4.6 and Step 3 share?

16 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Step 3 has 17.

Related comparisons

Go deeper