Noometry

Model comparison

Claude Fable 5 vs GPT-4o

Claude Fable 5 is the stronger model overall, scoring 66.8 to 28.6 on the Noometry Index. GPT-4o costs 4.6× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.

Last verified . 34 shared benchmarks.

Claude Fable 5 Anthropic

66.8

Rank #5 Confirmed

GPT-4o OpenAI

28.6

Rank #324 Confirmed

Summary

  • They share 34 benchmarks with published results for both. Claude Fable 5 scores higher in 10 categories and GPT-4o in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Fable 5 leads 88.5 to 10.6.
  • The biggest single-benchmark swing is ARC-AGI-1: 98.5% for Claude Fable 5 and 4.5% for GPT-4o.
  • GPT-4o is cheaper at $2.50 / $10 per million input/output tokens, against $10 / $50 for Claude Fable 5.
  • Claude Fable 5 accepts more context: 1M tokens versus 128K.

Side by side

Claude Fable 5GPT-4o
ProviderAnthropicOpenAI
Noometry Index66.828.6
Released2026-06-072024-05-13
WeightsProprietaryProprietary
Context window1M128K
Max output128K16K
Input $ / M tokens$10$2.50
Output $ / M tokens$50$10
Results tracked6272

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), GPT-4o: 24.8 (#328)

BenchmarkClaude Fable 5GPT-4o
GSO78.4%0%
WeirdML91.9%25.1%
LMArena Coding15191297
SWE-bench Verified—31%
DeepSWE69.9%—
FrontierCode53.5%—
SWE-bench Verified (bash only)—21.6%
Aider Polyglot—45.3%
LMArena WebDev1625—
FrontierSWE47%—
SciCode61%—
BigCodeBench Instruct—51.1%
LiveBench Coding—51.4%
MirrorCode63.9%—
BigCodeBench Complete—61.1%
CadEval—26%
ALE-Bench2,041—
HumanEval+—87.2%
MBPP+—72.2%

Agentic & Tool Use Claude Fable 5 leads

Claude Fable 5: 54.0 (#2), GPT-4o: 21.0 (#141)

BenchmarkClaude Fable 5GPT-4o
LMArena Search12301006
APEX-Agents63.6%—
GDPval—9.9%
Remote Labor Index16.1%—
TheAgentCompany—8.6%
τ²-bench Banking39.7%—
Cybench—12.5%
PostTrainBench41.8%—
BALROG—32.3%
GBAEval74.5%—
GDP.pdf30%—
METR Time Horizons—40.8%
Vending-Bench 25,680—

Reasoning Claude Fable 5 leads

Claude Fable 5: 76.8 (#6), GPT-4o: 9.4 (#343)

BenchmarkClaude Fable 5GPT-4o
ARC-AGI-289.2%0%
SimpleBench81.9%17.8%
ARC-AGI-198.5%4.5%
CritPt28.6%0%
Chess Puzzles41%13%
EnigmaEval39.3%0.8%
LMArena Hard Prompts15081281
DTBench98.4%64.5%
LMCA61.1%16.6%
Epoch Capabilities Index162.06128.97
Kagi LLM Benchmark91.4%—
NYT Connections (extended)92.7%—
EBR-Bench39.5%—
LiveBench Reasoning—55.8%
Mystery Game Puzzles52%—
LiveBench Data Analysis—60.9%
Surface Evolver Bench95%—
Bench to the Future 30.13—
ForecastBench—57.7
LiveBench—55.3%

Math Claude Fable 5 leads

Claude Fable 5: 88.5 (#5), GPT-4o: 10.6 (#312)

BenchmarkClaude Fable 5GPT-4o
FrontierMath (Tiers 1-3)87%0.4%
OTIS Mock AIME 2024-2025100%6.4%
LMArena Math15191285
FrontierMath Tier 490.2%—
ProofBench95%—
Omni-MATH—29.3%
LiveBench Math—49.5%
MATH Level 5—53.3%
FrontierMath (Feb 2025 set)—0.3%
FrontierMath Erdős0%—

Knowledge Claude Fable 5 leads

Claude Fable 5: 62.2 (#25), GPT-4o: 28.8 (#242)

BenchmarkClaude Fable 5GPT-4o
GPQA Diamond85.9%49.2%
SimpleQA Verified70.7%26%
LMArena Expert15341250
Humanity's Last Exam—2.7%
MMLU-Pro—71.3%
Confabulations—15.3%
Vectara Hallucination Rate—9.6%
GPQA (HELM)—52%
MMLU—88.1%

Multimodal Claude Fable 5 leads

Claude Fable 5: 45.3 (#17), GPT-4o: 34.5 (#91)

BenchmarkClaude Fable 5GPT-4o
LMArena Vision13241137
Video-MME—71.9%
GeoBench—71%
VPCT—40%
Blueprint-Bench 238.6%—
Furniture Assembly35.8%—
LMArena Document1496—
ScienceQA—88.5%

Multilingual Claude Fable 5 leads

Claude Fable 5: 57.3 (#9), GPT-4o: 43.2 (#186)

BenchmarkClaude Fable 5GPT-4o
LMArena Non-English14811283
LMArena Chinese15431277
LMArena French15051304
LMArena German14861282
LMArena Japanese15061257
LMArena Korean14881234
LMArena Russian15041286
LMArena Spanish14981292

Instruction Following Claude Fable 5 leads

Claude Fable 5: 78.6 (#8), GPT-4o: 66.6 (#207)

BenchmarkClaude Fable 5GPT-4o
LMArena Instruction Following15021278
LiveBench Instruction Following—68.6%
IFEval—81.7%

Long Context Claude Fable 5 leads

Claude Fable 5: 46.3 (#23), GPT-4o: 39.4 (#179)

BenchmarkClaude Fable 5GPT-4o
LMArena Longer Query15091289
Fiction.LiveBench—66.7%

Writing & Preference Claude Fable 5 leads

Claude Fable 5: 75.9 (#5), GPT-4o: 52.6 (#166)

BenchmarkClaude Fable 5GPT-4o
LMArena Text14911300
LMArena Creative Writing14941292
LMArena Multi-Turn15041302
Short-Story Creative Writing—81.8%
EQ-Bench Creative Writing1943—
WildBench—82.8%
EQ-Bench 41340—
LiveBench Language—47.6%

Frequently asked questions

Is Claude Fable 5 better than GPT-4o?

Claude Fable 5 is the stronger model overall, scoring 66.8 to 28.6 on the Noometry Index. GPT-4o costs 4.6× 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 GPT-4o?

GPT-4o is cheaper. It lists at $2.50 per million input tokens and $10 per million output tokens; Claude Fable 5 lists at $10 and $50.

Is Claude Fable 5 or GPT-4o better for coding?

Claude Fable 5 scores higher on coding benchmarks: 70.6 versus 24.8 in the Noometry coding category.

Which has the bigger context window?

Claude Fable 5 does, with 1M tokens against 128K.

How many benchmarks do Claude Fable 5 and GPT-4o share?

34 benchmarks have published results for both models. Claude Fable 5 has 62 scored results on Noometry and GPT-4o has 72.

Related comparisons

Go deeper