Noometry

Model comparison

Claude Fable 5.1 vs Claude Sonnet 4

Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 40.8 on the Noometry Index. Claude Sonnet 4 costs 3.3× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.

Last verified . 31 shared benchmarks.

Claude Fable 5.1 Anthropic

69.0

Rank #2 Confirmed

Claude Sonnet 4 Anthropic

40.8

Rank #145 Confirmed

Summary

  • They share 31 benchmarks with published results for both. Claude Fable 5.1 scores higher in 10 categories and Claude Sonnet 4 in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Fable 5.1 leads 76.7 to 22.9.
  • The biggest single-benchmark swing is ARC-AGI-2: 90% for Claude Fable 5.1 and 5.9% for Claude Sonnet 4.
  • Claude Sonnet 4 is cheaper at $3 / $15 per million input/output tokens, against $10 / $50 for Claude Fable 5.1.
  • Claude Fable 5.1 accepts more context: 1M tokens versus 200K.

Side by side

Claude Fable 5.1Claude Sonnet 4
ProviderAnthropicAnthropic
Noometry Index69.040.8
Released2026-09-012025-05-22
WeightsProprietaryProprietary
Context window1M200K
Max output128K64K
Input $ / M tokens$10$3
Output $ / M tokens$50$15
Results tracked5258

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: 74.7 (#1), Claude Sonnet 4: 43.5 (#88)

BenchmarkClaude Fable 5.1Claude Sonnet 4
SciCode63.1%40%
GSO88.2%4.9%
WeirdML92.9%46.1%
LMArena Coding15281414
ALE-Bench2,143655.35
FrontierCode50.9%—
SWE-bench Verified (bash only)—64.9%
Aider Polyglot—61.3%
CursorBench51.8%—
LMArena WebDev1744—
FrontierSWE56.3%—
MirrorCode73.3%—

Agentic & Tool Use Claude Fable 5.1 leads

Claude Fable 5.1: 50.7 (#5), Claude Sonnet 4: 38.5 (#31)

BenchmarkClaude Fable 5.1Claude Sonnet 4
APEX-Agents68.6%—
Remote Labor Index17.9%—
TheAgentCompany—33.1%
Cybench—35%
DeepResearch Bench—46.6%
OSWorld—43.9%
GDP.pdf29.6%—
METR Time Horizons—62%
Vending-Bench 25,422—

Reasoning Claude Fable 5.1 leads

Claude Fable 5.1: 76.7 (#7), Claude Sonnet 4: 22.9 (#187)

BenchmarkClaude Fable 5.1Claude Sonnet 4
ARC-AGI-290%5.9%
ARC-AGI-197.5%40%
CritPt31.1%0.3%
LMArena Hard Prompts15261372
DTBench97.6%77.1%
LMCA65.5%29%
Epoch Capabilities Index164.7141.69
SimpleBench—45.5%
Kagi LLM Benchmark—73%
NYT Connections (extended)90%—
Chess Puzzles47%—
EnigmaEval—3.1%
EBR-Bench57.1%—
Mystery Game Puzzles58%—
ForecastBench—60.2

Math Claude Fable 5.1 leads

Claude Fable 5.1: 89.6 (#4), Claude Sonnet 4: 43.3 (#80)

BenchmarkClaude Fable 5.1Claude Sonnet 4
OTIS Mock AIME 2024-2025100%71.1%
LMArena Math15251375
FrontierMath (Tiers 1-3)90.2%—
FrontierMath Tier 487.8%—
ProofBench100%—
Omni-MATH—60.2%
MATH Level 5—84.4%
FrontierMath (Feb 2025 set)—4.1%
FrontierMath Erdős0%—
FrontierMath Tier 4 (v1)—0%

Knowledge Claude Fable 5.1 leads

Claude Fable 5.1: 69.6 (#6), Claude Sonnet 4: 41.8 (#108)

BenchmarkClaude Fable 5.1Claude Sonnet 4
Humanity's Last Exam46.5%7.8%
LMArena Expert15351372
GPQA Diamond—79.2%
SimpleQA Verified70.8%—
MMLU-Pro—84.3%
Confabulations—13.2%
Vectara Hallucination Rate—10.3%
GPQA (HELM)—70.6%

Multimodal Claude Fable 5.1 leads

Claude Fable 5.1: 53.9 (#4), Claude Sonnet 4: 26.2 (#121)

BenchmarkClaude Fable 5.1Claude Sonnet 4
LMArena Vision13181191
GeoBench—37%
VPCT—34%
Blueprint-Bench 241.9%—
Furniture Assembly70%—
LMArena Document1513—
MindCube—44.8%

Multilingual Claude Fable 5.1 leads

Claude Fable 5.1: 59.1 (#3), Claude Sonnet 4: 46.7 (#156)

BenchmarkClaude Fable 5.1Claude Sonnet 4
LMArena Non-English15071333
LMArena Chinese15861350
LMArena French15251363
LMArena German15001331
LMArena Japanese15431302
LMArena Korean15341291
LMArena Russian15211355
LMArena Spanish15161357

Instruction Following Claude Fable 5.1 leads

Claude Fable 5.1: 79.2 (#6), Claude Sonnet 4: 71.7 (#145)

BenchmarkClaude Fable 5.1Claude Sonnet 4
LMArena Instruction Following15171376
IFEval—84%

Long Context Claude Fable 5.1 leads

Claude Fable 5.1: 46.7 (#20), Claude Sonnet 4: 33.7 (#259)

BenchmarkClaude Fable 5.1Claude Sonnet 4
LMArena Longer Query15221398
Fiction.LiveBench—46.9%

Writing & Preference Claude Fable 5.1 leads

Claude Fable 5.1: 79.2 (#2), Claude Sonnet 4: 57.1 (#132)

BenchmarkClaude Fable 5.1Claude Sonnet 4
LMArena Text15101351
LMArena Creative Writing15071345
EQ-Bench Creative Writing21621483
LMArena Multi-Turn14921376
Short-Story Creative Writing—81.4%
WildBench—83.8%

Frequently asked questions

Is Claude Fable 5.1 better than Claude Sonnet 4?

Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 40.8 on the Noometry Index. Claude Sonnet 4 costs 3.3× 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 Claude Sonnet 4?

Claude Sonnet 4 is cheaper. It lists at $3 per million input tokens and $15 per million output tokens; Claude Fable 5.1 lists at $10 and $50.

Is Claude Fable 5.1 or Claude Sonnet 4 better for coding?

Claude Fable 5.1 scores higher on coding benchmarks: 74.7 versus 43.5 in the Noometry coding category.

Which has the bigger context window?

Claude Fable 5.1 does, with 1M tokens against 200K.

How many benchmarks do Claude Fable 5.1 and Claude Sonnet 4 share?

31 benchmarks have published results for both models. Claude Fable 5.1 has 52 scored results on Noometry and Claude Sonnet 4 has 58.

Related comparisons

Go deeper