Noometry

Model comparison

Claude Fable 5 vs o4-mini

Claude Fable 5 is the stronger model overall, scoring 66.8 to 41.6 on the Noometry Index. o4-mini costs 10× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.

Last verified . 37 shared benchmarks.

Claude Fable 5 Anthropic

66.8

Rank #5 Confirmed

o4-mini OpenAI

41.6

Rank #132 Confirmed

Summary

  • They share 37 benchmarks with published results for both. Claude Fable 5 scores higher in 10 categories and o4-mini in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Fable 5 leads 76.8 to 24.6.
  • The biggest single-benchmark swing is FrontierMath Tier 4: 90.2% for Claude Fable 5 and 4.9% for o4-mini.
  • o4-mini is cheaper at $1.10 / $4.40 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 5o4-mini
ProviderAnthropicOpenAI
Noometry Index66.841.6
Released2026-06-072025-04-16
WeightsProprietaryProprietary
Context window1M200K
Max output128K100K
Input $ / M tokens$10$1.10
Output $ / M tokens$50$4.40
Results tracked6260

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), o4-mini: 40.9 (#127)

BenchmarkClaude Fable 5o4-mini
GSO78.4%3.6%
WeirdML91.9%52.6%
LMArena Coding15191368
ALE-Bench2,041826.17
DeepSWE69.9%—
FrontierCode53.5%—
SWE-bench Verified (bash only)—45%
Aider Polyglot—72%
LMArena WebDev1625—
FrontierSWE47%—
SciCode61%—
MirrorCode63.9%—
CadEval—62%
AlgoTune—1.72

Agentic & Tool Use Claude Fable 5 leads

Claude Fable 5: 54.0 (#2), o4-mini: 32.6 (#61)

BenchmarkClaude Fable 5o4-mini
APEX-Agents63.6%—
Berkeley Function Calling Leaderboard—53.2%
GDPval—25.3%
Remote Labor Index16.1%—
τ²-bench Banking39.7%—
PostTrainBench41.8%—
GBAEval74.5%—
GDP.pdf30%—
LMArena Search1230—
METR Time Horizons—63.9%
Vending-Bench 25,680—

Reasoning Claude Fable 5 leads

Claude Fable 5: 76.8 (#6), o4-mini: 24.6 (#162)

BenchmarkClaude Fable 5o4-mini
ARC-AGI-289.2%6.1%
SimpleBench81.9%38.7%
Kagi LLM Benchmark91.4%67.6%
ARC-AGI-198.5%58.7%
CritPt28.6%0.6%
Chess Puzzles41%26%
EnigmaEval39.3%9.2%
LMArena Hard Prompts15081351
Mystery Game Puzzles52%5%
DTBench98.4%77.6%
LMCA61.1%26.5%
Epoch Capabilities Index162.06145.64
NYT Connections (extended)92.7%—
EBR-Bench39.5%—
Surface Evolver Bench95%—
Bench to the Future 30.13—
ForecastBench—61.8

Math Claude Fable 5 leads

Claude Fable 5: 88.5 (#5), o4-mini: 40.8 (#89)

BenchmarkClaude Fable 5o4-mini
FrontierMath (Tiers 1-3)87%36.1%
FrontierMath Tier 490.2%4.9%
OTIS Mock AIME 2024-2025100%81.7%
LMArena Math15191389
ProofBench95%—
Omni-MATH—72%
MATH Level 5—97.8%
FrontierMath (Feb 2025 set)—24.8%
FrontierMath Erdős0%—
FrontierMath Tier 4 (v1)—6.3%

Knowledge Claude Fable 5 leads

Claude Fable 5: 62.2 (#25), o4-mini: 43.6 (#91)

BenchmarkClaude Fable 5o4-mini
GPQA Diamond85.9%79.6%
SimpleQA Verified70.7%19.6%
LMArena Expert15341343
Humanity's Last Exam—18.1%
MMLU-Pro—82%
Confabulations—15.8%
Vectara Hallucination Rate—18.6%
GPQA (HELM)—73.5%

Multimodal Claude Fable 5 leads

Claude Fable 5: 45.3 (#17), o4-mini: 40.2 (#49)

BenchmarkClaude Fable 5o4-mini
LMArena Vision13241194
GeoBench—64%
VPCT—57.5%
Blueprint-Bench 238.6%—
Furniture Assembly35.8%—
LMArena Document1496—

Multilingual Claude Fable 5 leads

Claude Fable 5: 57.3 (#9), o4-mini: 47.0 (#154)

BenchmarkClaude Fable 5o4-mini
LMArena Non-English14811337
LMArena Chinese15431354
LMArena French15051364
LMArena German14861336
LMArena Japanese15061308
LMArena Korean14881312
LMArena Russian15041334
LMArena Spanish14981347

Instruction Following Claude Fable 5 leads

Claude Fable 5: 78.6 (#8), o4-mini: 75.2 (#68)

BenchmarkClaude Fable 5o4-mini
LMArena Instruction Following15021321
IFEval—92.8%

Long Context Too close to call

Claude Fable 5: 46.3 (#23), o4-mini: 45.5 (#33)

BenchmarkClaude Fable 5o4-mini
LMArena Longer Query15091315
Fiction.LiveBench—77.8%

Writing & Preference Claude Fable 5 leads

Claude Fable 5: 75.9 (#5), o4-mini: 54.0 (#152)

BenchmarkClaude Fable 5o4-mini
LMArena Text14911353
LMArena Creative Writing14941294
LMArena Multi-Turn15041350
Short-Story Creative Writing—75%
EQ-Bench Creative Writing1943—
WildBench—85.4%
EQ-Bench 41340—

Frequently asked questions

Is Claude Fable 5 better than o4-mini?

Claude Fable 5 is the stronger model overall, scoring 66.8 to 41.6 on the Noometry Index. o4-mini costs 10× 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 o4-mini?

o4-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; Claude Fable 5 lists at $10 and $50.

Is Claude Fable 5 or o4-mini better for coding?

Claude Fable 5 scores higher on coding benchmarks: 70.6 versus 40.9 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 o4-mini share?

37 benchmarks have published results for both models. Claude Fable 5 has 62 scored results on Noometry and o4-mini has 60.

Related comparisons

Go deeper