Noometry

Model comparison

Claude Fable 5 vs GPT-5

Claude Fable 5 is the stronger model overall, scoring 66.8 to 50.9 on the Noometry Index. GPT-5 costs 5.8× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.

Last verified . 44 shared benchmarks.

Claude Fable 5 Anthropic

66.8

Rank #5 Confirmed

GPT-5 OpenAI

50.9

Rank #45 Confirmed

Summary

  • They share 44 benchmarks with published results for both. Claude Fable 5 scores higher in 8 categories and GPT-5 in 2 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Fable 5 leads 76.8 to 38.3.
  • The biggest single-benchmark swing is ARC-AGI-2: 89.2% for Claude Fable 5 and 9.9% for GPT-5.
  • GPT-5 is cheaper at $1.25 / $10 per million input/output tokens, against $10 / $50 for Claude Fable 5.
  • Claude Fable 5 accepts more context: 1M tokens versus 400K.

Side by side

Claude Fable 5GPT-5
ProviderAnthropicOpenAI
Noometry Index66.850.9
Released2026-06-072025-08-07
WeightsProprietaryProprietary
Context window1M400K
Max output128K128K
Input $ / M tokens$10$1.25
Output $ / M tokens$50$10
Results tracked6269

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-5: 50.3 (#47)

BenchmarkClaude Fable 5GPT-5
LMArena WebDev16251418
SciCode61%42.9%
GSO78.4%6.9%
WeirdML91.9%60.7%
LMArena Coding15191436
ALE-Bench2,0411,162
SWE-bench Verified—73.6%
DeepSWE69.9%—
FrontierCode53.5%—
SWE-bench Verified (bash only)—65%
Aider Polyglot—88%
FrontierSWE47%—
MirrorCode63.9%—
AlgoTune—1.67

Agentic & Tool Use Claude Fable 5 leads

Claude Fable 5: 54.0 (#2), GPT-5: 33.1 (#56)

BenchmarkClaude Fable 5GPT-5
Remote Labor Index16.1%1.7%
LMArena Search12301133
Terminal-Bench—49.6%
APEX-Agents63.6%—
GDPval—34.8%
τ²-bench Banking39.7%—
DeepResearch Bench—49.6%
PostTrainBench41.8%—
BALROG—32.8%
GBAEval74.5%—
GDP.pdf30%—
METR Time Horizons—69.6%
Vending-Bench 25,680—

Reasoning Claude Fable 5 leads

Claude Fable 5: 76.8 (#6), GPT-5: 38.3 (#64)

BenchmarkClaude Fable 5GPT-5
ARC-AGI-289.2%9.9%
SimpleBench81.9%56.7%
Kagi LLM Benchmark91.4%72.7%
ARC-AGI-198.5%65.7%
CritPt28.6%12.6%
Chess Puzzles41%37%
EnigmaEval39.3%10.5%
EBR-Bench39.5%12.7%
LMArena Hard Prompts15081416
Mystery Game Puzzles52%23%
DTBench98.4%90.7%
LMCA61.1%40%
Epoch Capabilities Index162.06150
NYT Connections (extended)92.7%—
Surface Evolver Bench95%—
Bench to the Future 30.13—
ForecastBench—61.4

Math Claude Fable 5 leads

Claude Fable 5: 88.5 (#5), GPT-5: 55.0 (#44)

BenchmarkClaude Fable 5GPT-5
FrontierMath (Tiers 1-3)87%55.4%
FrontierMath Tier 490.2%22%
OTIS Mock AIME 2024-2025100%91.4%
ProofBench95%18%
LMArena Math15191407
Omni-MATH—64.7%
MATH Level 5—98.1%
FrontierMath (Feb 2025 set)—32.4%
FrontierMath Erdős0%—
FrontierMath Tier 4 (v1)—12.5%

Knowledge Claude Fable 5 leads

Claude Fable 5: 62.2 (#25), GPT-5: 56.6 (#43)

BenchmarkClaude Fable 5GPT-5
GPQA Diamond85.9%86.2%
SimpleQA Verified70.7%50.1%
LMArena Expert15341419
Humanity's Last Exam—25.3%
MMLU-Pro—86.3%
Confabulations—10.3%
Vectara Hallucination Rate—14.7%
GPQA (HELM)—79.2%

Multimodal GPT-5 leads

Claude Fable 5: 45.3 (#17), GPT-5: 46.8 (#13)

BenchmarkClaude Fable 5GPT-5
LMArena Vision13241232
GeoBench—81%
VPCT—66%
Blueprint-Bench 238.6%—
Furniture Assembly35.8%—
LMArena Document1496—

Multilingual Claude Fable 5 leads

Claude Fable 5: 57.3 (#9), GPT-5: 51.4 (#110)

BenchmarkClaude Fable 5GPT-5
LMArena Non-English14811397
LMArena Chinese15431422
LMArena French15051410
LMArena German14861416
LMArena Japanese15061409
LMArena Korean14881360
LMArena Russian15041406
LMArena Spanish14981399

Instruction Following Claude Fable 5 leads

Claude Fable 5: 78.6 (#8), GPT-5: 73.8 (#113)

BenchmarkClaude Fable 5GPT-5
LMArena Instruction Following15021388
IFEval—87.5%

Long Context GPT-5 leads

Claude Fable 5: 46.3 (#23), GPT-5: 69.5 (#2)

BenchmarkClaude Fable 5GPT-5
LMArena Longer Query15091399
Fiction.LiveBench—97.2%

Writing & Preference Claude Fable 5 leads

Claude Fable 5: 75.9 (#5), GPT-5: 63.4 (#65)

BenchmarkClaude Fable 5GPT-5
LMArena Text14911406
LMArena Creative Writing14941365
EQ-Bench Creative Writing19431627
LMArena Multi-Turn15041426
Short-Story Creative Writing—86%
WildBench—85.7%
EQ-Bench 41340—

Frequently asked questions

Is Claude Fable 5 better than GPT-5?

Claude Fable 5 is the stronger model overall, scoring 66.8 to 50.9 on the Noometry Index. GPT-5 costs 5.8× 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-5?

GPT-5 is cheaper. It lists at $1.25 per million input tokens and $10 per million output tokens; Claude Fable 5 lists at $10 and $50.

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

Claude Fable 5 scores higher on coding benchmarks: 70.6 versus 50.3 in the Noometry coding category.

Which has the bigger context window?

Claude Fable 5 does, with 1M tokens against 400K.

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

44 benchmarks have published results for both models. Claude Fable 5 has 62 scored results on Noometry and GPT-5 has 69.

Related comparisons

Go deeper