Noometry

Model comparison

Claude Fable 5.1 vs Step 3.7 Flash

Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 36.5 on the Noometry Index. Step 3.7 Flash costs 48× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.

Last verified . 4 shared benchmarks.

Claude Fable 5.1 Anthropic

68.5

Rank #2 Confirmed

Step 3.7 Flash StepFun

36.5

Rank #207 Reported

Summary

  • They share 4 benchmarks with published results for both. Claude Fable 5.1 scores higher in 3 categories and Step 3.7 Flash in 0 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Fable 5.1 leads 76.7 to 20.9.
  • The biggest single-benchmark swing is NYT Connections (extended): 90% for Claude Fable 5.1 and 39.7% for Step 3.7 Flash.
  • Step 3.7 Flash is cheaper at $0.18 / $1.11 per million input/output tokens, against $10 / $50 for Claude Fable 5.1.
  • Claude Fable 5.1 accepts more context: 1M tokens versus 256K.
  • Step 3.7 Flash has downloadable open weights; the other is API-only.

Side by side

Claude Fable 5.1Step 3.7 Flash
ProviderAnthropicStepFun
Noometry Index68.536.5
Released2026-09-012026-05-29
WeightsProprietaryOpen
Context window1M256K
Max output128K256K
Input $ / M tokens$10$0.18
Output $ / M tokens$50$1.11
Results tracked505

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

Category by category

Coding Claude Fable 5.1 leads

Claude Fable 5.1: 70.5 (#2), Step 3.7 Flash: 39.4 (#147)

BenchmarkClaude Fable 5.1Step 3.7 Flash
SciCode63.1%40%
ALE-Bench2,143694.12
FrontierCode50.9%—
CursorBench51.8%—
LMArena WebDev1753—
FrontierSWE56.3%—
WeirdML92.9%—
LMArena Coding1523—
MirrorCode73.3%—

Agentic & Tool Use Not comparable

Claude Fable 5.1: 50.8 (#5), Step 3.7 Flash: —

BenchmarkClaude Fable 5.1Step 3.7 Flash
APEX-Agents68.6%—
Remote Labor Index17.9%—
GDP.pdf29.6%—
Vending-Bench 25,422—

Reasoning Claude Fable 5.1 leads

Claude Fable 5.1: 76.7 (#5), Step 3.7 Flash: 20.9 (#211)

BenchmarkClaude Fable 5.1Step 3.7 Flash
NYT Connections (extended)90%39.7%
CritPt31.1%2.3%
ARC-AGI-290%—
ARC-AGI-197.5%—
Chess Puzzles47%—
EBR-Bench57.1%—
LMArena Hard Prompts1526—
Mystery Game Puzzles58%—
DTBench97.6%—
LMCA65.5%—
Epoch Capabilities Index165—

Math Claude Fable 5.1 leads

Claude Fable 5.1: 89.5 (#3), Step 3.7 Flash: 40.9 (#74)

BenchmarkClaude Fable 5.1Step 3.7 Flash
FrontierMath (Tiers 1-3)90.2%—
FrontierMath Tier 487.8%—
MathArena Final-Answer Competitions—68.5%
OTIS Mock AIME 2024-2025100%—
ProofBench100%—
LMArena Math1519—
FrontierMath Erdős0%—

Knowledge Not comparable

Claude Fable 5.1: 69.3 (#5), Step 3.7 Flash: —

BenchmarkClaude Fable 5.1Step 3.7 Flash
Humanity's Last Exam46.5%—
SimpleQA Verified70.8%—
LMArena Expert1528—

Multimodal Not comparable

Claude Fable 5.1: 54.1 (#4), Step 3.7 Flash: —

BenchmarkClaude Fable 5.1Step 3.7 Flash
LMArena Vision1319—
Blueprint-Bench 241.9%—
Furniture Assembly70%—
LMArena Document1513—

Multilingual Not comparable

Claude Fable 5.1: 59.5 (#2), Step 3.7 Flash: —

BenchmarkClaude Fable 5.1Step 3.7 Flash
LMArena Non-English1509—
LMArena Chinese1589—
LMArena French1532—
LMArena German1495—
LMArena Japanese1565—
LMArena Russian1525—
LMArena Spanish1503—

Instruction Following Not comparable

Claude Fable 5.1: 79.3 (#6), Step 3.7 Flash: —

BenchmarkClaude Fable 5.1Step 3.7 Flash
LMArena Instruction Following1515—

Long Context Not comparable

Claude Fable 5.1: 46.8 (#19), Step 3.7 Flash: —

BenchmarkClaude Fable 5.1Step 3.7 Flash
LMArena Longer Query1524—

Writing & Preference Not comparable

Claude Fable 5.1: 79.3 (#1), Step 3.7 Flash: —

BenchmarkClaude Fable 5.1Step 3.7 Flash
LMArena Text1511—
LMArena Creative Writing1507—
EQ-Bench Creative Writing2162—
LMArena Multi-Turn1492—

Frequently asked questions

Is Claude Fable 5.1 better than Step 3.7 Flash?

Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 36.5 on the Noometry Index. Step 3.7 Flash costs 48× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.

Which is cheaper, Claude Fable 5.1 or Step 3.7 Flash?

Step 3.7 Flash is cheaper. It lists at $0.18 per million input tokens and $1.11 per million output tokens; Claude Fable 5.1 lists at $10 and $50.

Is Claude Fable 5.1 or Step 3.7 Flash better for coding?

Claude Fable 5.1 scores higher on coding benchmarks: 70.5 versus 39.4 in the Noometry coding category.

Which has the bigger context window?

Claude Fable 5.1 does, with 1M tokens against 256K.

How many benchmarks do Claude Fable 5.1 and Step 3.7 Flash share?

4 benchmarks have published results for both models. Claude Fable 5.1 has 50 scored results on Noometry and Step 3.7 Flash has 5.

Related comparisons

Go deeper