Noometry

Model comparison

Claude Fable 5 vs Claude Fable 5.1

Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 66.8 on the Noometry Index.

Last verified . 50 shared benchmarks.

Claude Fable 5 Anthropic

66.8

Rank #5 Confirmed

Claude Fable 5.1 Anthropic

69.0

Rank #2 Confirmed

Summary

  • They share 50 benchmarks with published results for both. Claude Fable 5 scores higher in 2 categories and Claude Fable 5.1 in 8 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in multimodal, where Claude Fable 5.1 leads 53.9 to 45.3.
  • The biggest single-benchmark swing is Furniture Assembly: 35.8% for Claude Fable 5 and 70% for Claude Fable 5.1.
  • Both cost about the same: $10 input and $50 output per million tokens.

Side by side

Claude Fable 5Claude Fable 5.1
ProviderAnthropicAnthropic
Noometry Index66.869.0
Released2026-06-072026-09-01
WeightsProprietaryProprietary
Context window1M1M
Max output128K128K
Input $ / M tokens$10$10
Output $ / M tokens$50$50
Results tracked6252

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

Category by category

Coding Claude Fable 5.1 leads

Claude Fable 5: 70.6 (#4), Claude Fable 5.1: 74.7 (#1)

BenchmarkClaude Fable 5Claude Fable 5.1
FrontierCode53.5%50.9%
LMArena WebDev16251744
FrontierSWE47%56.3%
SciCode61%63.1%
GSO78.4%88.2%
WeirdML91.9%92.9%
LMArena Coding15191528
MirrorCode63.9%73.3%
ALE-Bench2,0412,143
DeepSWE69.9%—
CursorBench—51.8%

Agentic & Tool Use Claude Fable 5 leads

Claude Fable 5: 54.0 (#2), Claude Fable 5.1: 50.7 (#5)

BenchmarkClaude Fable 5Claude Fable 5.1
APEX-Agents63.6%68.6%
Remote Labor Index16.1%17.9%
GDP.pdf30%29.6%
Vending-Bench 25,6805,422
τ²-bench Banking39.7%—
PostTrainBench41.8%—
GBAEval74.5%—
LMArena Search1230—

Reasoning Too close to call

Claude Fable 5: 76.8 (#6), Claude Fable 5.1: 76.7 (#7)

BenchmarkClaude Fable 5Claude Fable 5.1
ARC-AGI-289.2%90%
NYT Connections (extended)92.7%90%
ARC-AGI-198.5%97.5%
CritPt28.6%31.1%
Chess Puzzles41%47%
EBR-Bench39.5%57.1%
LMArena Hard Prompts15081526
Mystery Game Puzzles52%58%
DTBench98.4%97.6%
LMCA61.1%65.5%
Epoch Capabilities Index162.06164.7
SimpleBench81.9%—
Kagi LLM Benchmark91.4%—
EnigmaEval39.3%—
Surface Evolver Bench95%—
Bench to the Future 30.13—

Math Claude Fable 5.1 leads

Claude Fable 5: 88.5 (#5), Claude Fable 5.1: 89.6 (#4)

BenchmarkClaude Fable 5Claude Fable 5.1
FrontierMath (Tiers 1-3)87%90.2%
FrontierMath Tier 490.2%87.8%
OTIS Mock AIME 2024-2025100%100%
ProofBench95%100%
LMArena Math15191525
FrontierMath Erdős0%0%

Knowledge Claude Fable 5.1 leads

Claude Fable 5: 62.2 (#25), Claude Fable 5.1: 69.6 (#6)

BenchmarkClaude Fable 5Claude Fable 5.1
SimpleQA Verified70.7%70.8%
LMArena Expert15341535
GPQA Diamond85.9%—
Humanity's Last Exam—46.5%

Multimodal Claude Fable 5.1 leads

Claude Fable 5: 45.3 (#17), Claude Fable 5.1: 53.9 (#4)

BenchmarkClaude Fable 5Claude Fable 5.1
LMArena Vision13241318
Blueprint-Bench 238.6%41.9%
Furniture Assembly35.8%70%
LMArena Document14961513

Multilingual Claude Fable 5.1 leads

Claude Fable 5: 57.3 (#9), Claude Fable 5.1: 59.1 (#3)

BenchmarkClaude Fable 5Claude Fable 5.1
LMArena Non-English14811507
LMArena Chinese15431586
LMArena French15051525
LMArena German14861500
LMArena Japanese15061543
LMArena Korean14881534
LMArena Russian15041521
LMArena Spanish14981516

Instruction Following Too close to call

Claude Fable 5: 78.6 (#8), Claude Fable 5.1: 79.2 (#6)

BenchmarkClaude Fable 5Claude Fable 5.1
LMArena Instruction Following15021517

Long Context Too close to call

Claude Fable 5: 46.3 (#23), Claude Fable 5.1: 46.7 (#20)

BenchmarkClaude Fable 5Claude Fable 5.1
LMArena Longer Query15091522

Writing & Preference Claude Fable 5.1 leads

Claude Fable 5: 75.9 (#5), Claude Fable 5.1: 79.2 (#2)

BenchmarkClaude Fable 5Claude Fable 5.1
LMArena Text14911510
LMArena Creative Writing14941507
EQ-Bench Creative Writing19432162
LMArena Multi-Turn15041492
EQ-Bench 41340—

Frequently asked questions

Is Claude Fable 5 better than Claude Fable 5.1?

Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 66.8 on the Noometry Index.

Which is cheaper, Claude Fable 5 or Claude Fable 5.1?

Claude Fable 5.1 is cheaper. It lists at $10 per million input tokens and $50 per million output tokens; Claude Fable 5 lists at $10 and $50.

Is Claude Fable 5 or Claude Fable 5.1 better for coding?

Claude Fable 5.1 scores higher on coding benchmarks: 74.7 versus 70.6 in the Noometry coding category.

Which has the bigger context window?

Both accept 1M tokens.

How many benchmarks do Claude Fable 5 and Claude Fable 5.1 share?

50 benchmarks have published results for both models. Claude Fable 5 has 62 scored results on Noometry and Claude Fable 5.1 has 52.

Related comparisons

Go deeper