Noometry

Model comparison

Claude Fable 5 vs Claude Opus 4.5

Claude Fable 5 is the stronger model overall, scoring 66.3 to 50.5 on the Noometry Index. Claude Opus 4.5 costs 2.0× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.

Last verified . 45 shared benchmarks.

Claude Fable 5 Anthropic

66.3

Rank #5 Confirmed

Claude Opus 4.5 Anthropic

50.5

Rank #39 Confirmed

Summary

  • They share 45 benchmarks with published results for both. Claude Fable 5 scores higher in 9 categories and Claude Opus 4.5 in 1 category; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Fable 5 leads 88.4 to 38.5.
  • The biggest single-benchmark swing is FrontierMath Tier 4: 90.2% for Claude Fable 5 and 4.9% for Claude Opus 4.5.
  • Claude Opus 4.5 is cheaper at $5 / $25 per million input/output tokens, against $10 / $50 for Claude Fable 5.
  • Claude Fable 5 accepts more context: 1M tokens versus 200K.

Side by side

Claude Fable 5Claude Opus 4.5
ProviderAnthropicAnthropic
Noometry Index66.350.5
Released2026-06-072025-11-01
WeightsProprietaryProprietary
Context window1M200K
Max output128K64K
Input $ / M tokens$10$5
Output $ / M tokens$50$25
Results tracked6169

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

Category by category

Coding Claude Fable 5 leads

Claude Fable 5: 67.0 (#4), Claude Opus 4.5: 55.4 (#21)

BenchmarkClaude Fable 5Claude Opus 4.5
LMArena WebDev16261493
WeirdML91.9%63.7%
LMArena Coding15191504
ALE-Bench2,0411,025
SWE-bench Verified—76.7%
DeepSWE69.9%—
FrontierCode53.5%—
SWE-bench Verified (bash only)—76.8%
SWE-bench Multilingual—70.7%
FrontierSWE47%—
SciCode61%—
GSO—26.5%
MirrorCode63.9%—
AlgoTune—1.77

Agentic & Tool Use Claude Fable 5 leads

Claude Fable 5: 54.1 (#2), Claude Opus 4.5: 47.2 (#11)

BenchmarkClaude Fable 5Claude Opus 4.5
Remote Labor Index16.1%3.8%
τ²-bench Banking39.7%24.7%
LMArena Search12301180
Vending-Bench 25,6804,967
Terminal-Bench—63.1%
APEX-Agents63.6%—
Berkeley Function Calling Leaderboard—77.5%
GDPval—45.5%
τ²-bench Airline—84%
τ²-bench Retail—79.6%
τ²-bench Telecom—92.3%
Cybench—82%
DeepResearch Bench—54.8%
OSWorld—66.3%
PostTrainBench41.8%—
BALROG—43.5%
GBAEval74.5%—
GDP.pdf30%—
METR Time Horizons—75%

Reasoning Claude Fable 5 leads

Claude Fable 5: 76.8 (#4), Claude Opus 4.5: 42.5 (#43)

BenchmarkClaude Fable 5Claude Opus 4.5
ARC-AGI-289.2%37.6%
SimpleBench81.9%62%
Kagi LLM Benchmark91.4%80.2%
NYT Connections (extended)92.7%52.5%
ARC-AGI-198.5%80%
Chess Puzzles41%12%
EnigmaEval39.3%11.9%
EBR-Bench39.5%14.3%
LMArena Hard Prompts15081476
Mystery Game Puzzles52%22%
DTBench98.4%89.9%
LMCA61.1%44.5%
Epoch Capabilities Index163.6150.1
CritPt28.6%—
Surface Evolver Bench95%—
Bench to the Future 30.13—
ForecastBench—60.7

Math Claude Fable 5 leads

Claude Fable 5: 88.4 (#5), Claude Opus 4.5: 38.5 (#85)

BenchmarkClaude Fable 5Claude Opus 4.5
FrontierMath (Tiers 1-3)87%34.4%
FrontierMath Tier 490.2%4.9%
OTIS Mock AIME 2024-2025100%86.1%
ProofBench95%36%
LMArena Math15191463
FrontierMath (Feb 2025 set)—20.7%
FrontierMath Erdős0%—
FrontierMath Tier 4 (v1)—4.2%

Knowledge Claude Fable 5 leads

Claude Fable 5: 62.3 (#22), Claude Opus 4.5: 56.4 (#38)

BenchmarkClaude Fable 5Claude Opus 4.5
GPQA Diamond85.9%86%
SimpleQA Verified70.7%45.7%
LMArena Expert15341488
Humanity's Last Exam—25.2%
Vectara Hallucination Rate—10.9%

Multimodal Claude Fable 5 leads

Claude Fable 5: 45.6 (#14), Claude Opus 4.5: 31.1 (#99)

BenchmarkClaude Fable 5Claude Opus 4.5
Furniture Assembly35.8%28.3%
LMArena Document14961462
LMArena Vision1326—
GeoBench—75%
VPCT—40%
Blueprint-Bench 238.6%—

Multilingual Claude Fable 5 leads

Claude Fable 5: 57.6 (#8), Claude Opus 4.5: 54.5 (#45)

BenchmarkClaude Fable 5Claude Opus 4.5
LMArena Non-English14831438
LMArena Chinese15461470
LMArena French15091471
LMArena German14861449
LMArena Japanese15071415
LMArena Korean14931424
LMArena Russian15071448
LMArena Spanish15031455

Instruction Following Claude Fable 5 leads

Claude Fable 5: 78.8 (#7), Claude Opus 4.5: 77.7 (#20)

BenchmarkClaude Fable 5Claude Opus 4.5
LMArena Instruction Following15031478

Long Context Too close to call

Claude Fable 5: 46.3 (#22), Claude Opus 4.5: 46.4 (#21)

BenchmarkClaude Fable 5Claude Opus 4.5
LMArena Longer Query15101480
CL-bench—21.1%

Writing & Preference Claude Fable 5 leads

Claude Fable 5: 76.1 (#5), Claude Opus 4.5: 68.2 (#28)

BenchmarkClaude Fable 5Claude Opus 4.5
LMArena Text14911451
LMArena Creative Writing14941445
EQ-Bench Creative Writing19431687
LMArena Multi-Turn15051466
EQ-Bench 41340—

Frequently asked questions

Is Claude Fable 5 better than Claude Opus 4.5?

Claude Fable 5 is the stronger model overall, scoring 66.3 to 50.5 on the Noometry Index. Claude Opus 4.5 costs 2.0× 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 Opus 4.5?

Claude Opus 4.5 is cheaper. It lists at $5 per million input tokens and $25 per million output tokens; Claude Fable 5 lists at $10 and $50.

Is Claude Fable 5 or Claude Opus 4.5 better for coding?

Claude Fable 5 scores higher on coding benchmarks: 67.0 versus 55.4 in the Noometry coding category.

Which has the bigger context window?

Claude Fable 5 does, with 1M tokens against 200K.

How many benchmarks do Claude Fable 5 and Claude Opus 4.5 share?

45 benchmarks have published results for both models. Claude Fable 5 has 61 scored results on Noometry and Claude Opus 4.5 has 69.

Related comparisons

Go deeper