Noometry

Model comparison

Claude Fable 5 vs Claude Sonnet 4.6

Claude Fable 5 is the stronger model overall, scoring 66.8 to 50.3 on the Noometry Index. Claude Sonnet 4.6 costs 3.3× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.

Last verified . 46 shared benchmarks.

Claude Fable 5 Anthropic

66.8

Rank #5 Confirmed

Claude Sonnet 4.6 Anthropic

50.3

Rank #50 Confirmed

Summary

  • They share 46 benchmarks with published results for both. Claude Fable 5 scores higher in 10 categories and Claude Sonnet 4.6 in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Fable 5 leads 88.5 to 52.9.
  • The biggest single-benchmark swing is ProofBench: 95% for Claude Fable 5 and 45% for Claude Sonnet 4.6.
  • Claude Sonnet 4.6 is cheaper at $3 / $15 per million input/output tokens, against $10 / $50 for Claude Fable 5.

Side by side

Claude Fable 5Claude Sonnet 4.6
ProviderAnthropicAnthropic
Noometry Index66.850.3
Released2026-06-072026-02-17
WeightsProprietaryProprietary
Context window1M1M
Max output128K128K
Input $ / M tokens$10$3
Output $ / M tokens$50$15
Results tracked6257

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), Claude Sonnet 4.6: 46.3 (#67)

BenchmarkClaude Fable 5Claude Sonnet 4.6
DeepSWE69.9%29.9%
FrontierCode53.5%24.3%
LMArena WebDev16251522
SciCode61%46.8%
WeirdML91.9%66.1%
LMArena Coding15191504
ALE-Bench2,0411,327
SWE-bench Verified—75.2%
FrontierSWE47%—
GSO78.4%—
MirrorCode63.9%—

Agentic & Tool Use Claude Fable 5 leads

Claude Fable 5: 54.0 (#2), Claude Sonnet 4.6: 39.1 (#28)

BenchmarkClaude Fable 5Claude Sonnet 4.6
APEX-Agents63.6%43%
GBAEval74.5%48.8%
GDP.pdf30%18%
LMArena Search12301221
Vending-Bench 25,6807,204
Terminal-Bench—53.4%
OSWorld 2.0—9.3%
Remote Labor Index16.1%—
τ²-bench Banking39.7%—
DeepResearch Bench—54.9%
OSWorld—72.1%
PostTrainBench41.8%—
ExploitBench—23.6%

Reasoning Claude Fable 5 leads

Claude Fable 5: 76.8 (#6), Claude Sonnet 4.6: 46.1 (#45)

BenchmarkClaude Fable 5Claude Sonnet 4.6
ARC-AGI-289.2%60.4%
NYT Connections (extended)92.7%80.9%
ARC-AGI-198.5%86.5%
CritPt28.6%3.1%
Chess Puzzles41%13%
LMArena Hard Prompts15081484
Mystery Game Puzzles52%16%
DTBench98.4%89.9%
LMCA61.1%46.5%
Epoch Capabilities Index162.06152.24
SimpleBench81.9%—
Kagi LLM Benchmark91.4%—
EnigmaEval39.3%—
Thematic Generalization—76.3%
EBR-Bench39.5%—
Surface Evolver Bench95%—
Bench to the Future 30.13—
ForecastBench—62

Math Claude Fable 5 leads

Claude Fable 5: 88.5 (#5), Claude Sonnet 4.6: 52.9 (#49)

BenchmarkClaude Fable 5Claude Sonnet 4.6
OTIS Mock AIME 2024-2025100%85.8%
ProofBench95%45%
LMArena Math15191462
FrontierMath (Tiers 1-3)87%—
FrontierMath Tier 490.2%—
FrontierMath (Feb 2025 set)—32.4%
FrontierMath Erdős0%—
FrontierMath Tier 4 (v1)—8.3%

Knowledge Claude Fable 5 leads

Claude Fable 5: 62.2 (#25), Claude Sonnet 4.6: 51.7 (#65)

BenchmarkClaude Fable 5Claude Sonnet 4.6
GPQA Diamond85.9%87.4%
SimpleQA Verified70.7%35.5%
LMArena Expert15341500
Vectara Hallucination Rate—10.6%

Multimodal Claude Fable 5 leads

Claude Fable 5: 45.3 (#17), Claude Sonnet 4.6: 38.0 (#68)

BenchmarkClaude Fable 5Claude Sonnet 4.6
LMArena Vision13241283
Blueprint-Bench 238.6%6.7%
LMArena Document14961482
Furniture Assembly35.8%—

Multilingual Claude Fable 5 leads

Claude Fable 5: 57.3 (#9), Claude Sonnet 4.6: 54.4 (#41)

BenchmarkClaude Fable 5Claude Sonnet 4.6
LMArena Non-English14811440
LMArena Chinese15431491
LMArena French15051465
LMArena German14861428
LMArena Japanese15061420
LMArena Korean14881411
LMArena Russian15041440
LMArena Spanish14981464

Instruction Following Claude Fable 5 leads

Claude Fable 5: 78.6 (#8), Claude Sonnet 4.6: 77.4 (#25)

BenchmarkClaude Fable 5Claude Sonnet 4.6
LMArena Instruction Following15021475

Long Context Claude Fable 5 leads

Claude Fable 5: 46.3 (#23), Claude Sonnet 4.6: 45.3 (#44)

BenchmarkClaude Fable 5Claude Sonnet 4.6
LMArena Longer Query15091479

Writing & Preference Claude Fable 5 leads

Claude Fable 5: 75.9 (#5), Claude Sonnet 4.6: 70.2 (#22)

BenchmarkClaude Fable 5Claude Sonnet 4.6
LMArena Text14911458
LMArena Creative Writing14941435
EQ-Bench Creative Writing19431810
EQ-Bench 413401207
LMArena Multi-Turn15041464

Frequently asked questions

Is Claude Fable 5 better than Claude Sonnet 4.6?

Claude Fable 5 is the stronger model overall, scoring 66.8 to 50.3 on the Noometry Index. Claude Sonnet 4.6 costs 3.3× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.

Which is cheaper, Claude Fable 5 or Claude Sonnet 4.6?

Claude Sonnet 4.6 is cheaper. It lists at $3 per million input tokens and $15 per million output tokens; Claude Fable 5 lists at $10 and $50.

Is Claude Fable 5 or Claude Sonnet 4.6 better for coding?

Claude Fable 5 scores higher on coding benchmarks: 70.6 versus 46.3 in the Noometry coding category.

Which has the bigger context window?

Both accept 1M tokens.

How many benchmarks do Claude Fable 5 and Claude Sonnet 4.6 share?

46 benchmarks have published results for both models. Claude Fable 5 has 62 scored results on Noometry and Claude Sonnet 4.6 has 57.

Related comparisons

Go deeper