Noometry

Model comparison

Claude Fable 5 vs Step 3

Claude Fable 5 is the stronger model overall, scoring 66.8 to 40.5 on the Noometry Index.

Last verified . 17 shared benchmarks.

Claude Fable 5 Anthropic

66.8

Rank #5 Confirmed

Step 3 StepFun

40.5

Rank #149 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Claude Fable 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 Fable 5 leads 88.5 to 37.6.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 91.4% for Claude Fable 5 and 62.3% for Step 3.
  • Step 3 has downloadable open weights; the other is API-only.

Side by side

Claude Fable 5Step 3
ProviderAnthropicStepFun
Noometry Index66.840.5
Released2026-06-07—
WeightsProprietaryOpen
Context window1M—
Max output128K—
Input $ / M tokens$10—
Output $ / M tokens$50—
Results tracked6217

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

Category by category

Coding Claude Fable 5 leads

Claude Fable 5: 70.6 (#4), Step 3: 40.1 (#147)

BenchmarkClaude Fable 5Step 3
LMArena Coding15191367
DeepSWE69.9%—
FrontierCode53.5%—
LMArena WebDev1625—
FrontierSWE47%—
SciCode61%—
GSO78.4%—
WeirdML91.9%—
MirrorCode63.9%—
ALE-Bench2,041—

Agentic & Tool Use Not comparable

Claude Fable 5: 54.0 (#2), Step 3: —

BenchmarkClaude Fable 5Step 3
APEX-Agents63.6%—
Remote Labor Index16.1%—
τ²-bench Banking39.7%—
PostTrainBench41.8%—
GBAEval74.5%—
GDP.pdf30%—
LMArena Search1230—
Vending-Bench 25,680—

Reasoning Claude Fable 5 leads

Claude Fable 5: 76.8 (#6), Step 3: 28.4 (#105)

BenchmarkClaude Fable 5Step 3
Kagi LLM Benchmark91.4%62.3%
LMArena Hard Prompts15081355
ARC-AGI-289.2%—
SimpleBench81.9%—
NYT Connections (extended)92.7%—
ARC-AGI-198.5%—
CritPt28.6%—
Chess Puzzles41%—
EnigmaEval39.3%—
EBR-Bench39.5%—
Mystery Game Puzzles52%—
DTBench98.4%—
LMCA61.1%—
Surface Evolver Bench95%—
Bench to the Future 30.13—
Epoch Capabilities Index162.06—

Math Claude Fable 5 leads

Claude Fable 5: 88.5 (#5), Step 3: 37.6 (#148)

BenchmarkClaude Fable 5Step 3
LMArena Math15191366
FrontierMath (Tiers 1-3)87%—
FrontierMath Tier 490.2%—
OTIS Mock AIME 2024-2025100%—
ProofBench95%—
FrontierMath Erdős0%—

Knowledge Claude Fable 5 leads

Claude Fable 5: 62.2 (#25), Step 3: 36.8 (#164)

BenchmarkClaude Fable 5Step 3
LMArena Expert15341333
GPQA Diamond85.9%—
SimpleQA Verified70.7%—

Multimodal Claude Fable 5 leads

Claude Fable 5: 45.3 (#17), Step 3: 35.5 (#86)

BenchmarkClaude Fable 5Step 3
LMArena Vision13241177
Blueprint-Bench 238.6%—
Furniture Assembly35.8%—
LMArena Document1496—

Multilingual Claude Fable 5 leads

Claude Fable 5: 57.3 (#9), Step 3: 46.3 (#159)

BenchmarkClaude Fable 5Step 3
LMArena Non-English14811327
LMArena Chinese15431397
LMArena German14861371
LMArena Korean14881269
LMArena Russian15041331
LMArena Spanish14981371
LMArena French1505—
LMArena Japanese1506—

Instruction Following Claude Fable 5 leads

Claude Fable 5: 78.6 (#8), Step 3: 70.4 (#164)

BenchmarkClaude Fable 5Step 3
LMArena Instruction Following15021332

Long Context Claude Fable 5 leads

Claude Fable 5: 46.3 (#23), Step 3: 40.3 (#157)

BenchmarkClaude Fable 5Step 3
LMArena Longer Query15091326

Writing & Preference Claude Fable 5 leads

Claude Fable 5: 75.9 (#5), Step 3: 54.3 (#151)

BenchmarkClaude Fable 5Step 3
LMArena Text14911350
LMArena Creative Writing14941321
LMArena Multi-Turn15041341
EQ-Bench Creative Writing1943—
EQ-Bench 41340—

Frequently asked questions

Is Claude Fable 5 better than Step 3?

Claude Fable 5 is the stronger model overall, scoring 66.8 to 40.5 on the Noometry Index.

Is Claude Fable 5 or Step 3 better for coding?

Claude Fable 5 scores higher on coding benchmarks: 70.6 versus 40.1 in the Noometry coding category.

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

17 benchmarks have published results for both models. Claude Fable 5 has 62 scored results on Noometry and Step 3 has 17.

Related comparisons

Go deeper