Noometry

Model comparison

Claude Fable 5 vs GPT-5 Mini

Claude Fable 5 is the stronger model overall, scoring 66.3 to 41.7 on the Noometry Index. GPT-5 Mini costs 29× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.

Last verified . 39 shared benchmarks.

Claude Fable 5 Anthropic

66.3

Rank #5 Confirmed

GPT-5 Mini OpenAI

41.7

Rank #115 Confirmed

Summary

  • They share 39 benchmarks with published results for both. Claude Fable 5 scores higher in 10 categories and GPT-5 Mini in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Fable 5 leads 76.8 to 24.1.
  • The biggest single-benchmark swing is ProofBench: 95% for Claude Fable 5 and 9% for GPT-5 Mini.
  • GPT-5 Mini is cheaper at $0.25 / $2 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 Mini
ProviderAnthropicOpenAI
Noometry Index66.341.7
Released2026-06-072025-08-07
WeightsProprietaryProprietary
Context window1M400K
Max output128K128K
Input $ / M tokens$10$0.25
Output $ / M tokens$50$2
Results tracked6160

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), GPT-5 Mini: 40.0 (#134)

BenchmarkClaude Fable 5GPT-5 Mini
SciCode61%39.2%
WeirdML91.9%52.7%
LMArena Coding15191406
ALE-Bench2,041799.77
SWE-bench Verified—64.7%
DeepSWE69.9%—
FrontierCode53.5%—
SWE-bench Verified (bash only)—59.8%
LMArena WebDev1626—
SWE-bench Multilingual—39.7%
FrontierSWE47%—
MirrorCode63.9%—
AlgoTune—1.38

Agentic & Tool Use Claude Fable 5 leads

Claude Fable 5: 54.1 (#2), GPT-5 Mini: 31.0 (#64)

BenchmarkClaude Fable 5GPT-5 Mini
Vending-Bench 25,680-31.18
Terminal-Bench—34.8%
APEX-Agents63.6%—
Berkeley Function Calling Leaderboard—55.5%
Remote Labor Index16.1%—
τ²-bench Banking39.7%—
PostTrainBench41.8%—
GBAEval74.5%—
GDP.pdf30%—
LMArena Search1230—

Reasoning Claude Fable 5 leads

Claude Fable 5: 76.8 (#4), GPT-5 Mini: 24.1 (#153)

BenchmarkClaude Fable 5GPT-5 Mini
ARC-AGI-289.2%4.4%
Kagi LLM Benchmark91.4%70.3%
ARC-AGI-198.5%54.3%
CritPt28.6%0%
Chess Puzzles41%30%
EnigmaEval39.3%8.2%
LMArena Hard Prompts15081380
Mystery Game Puzzles52%10%
DTBench98.4%80.5%
LMCA61.1%34.2%
Epoch Capabilities Index163.6145.51
SimpleBench81.9%—
NYT Connections (extended)92.7%—
EBR-Bench39.5%—
Surface Evolver Bench95%—
Bench to the Future 30.13—
ForecastBench—61

Math Claude Fable 5 leads

Claude Fable 5: 88.4 (#5), GPT-5 Mini: 46.3 (#59)

BenchmarkClaude Fable 5GPT-5 Mini
FrontierMath (Tiers 1-3)87%46.7%
FrontierMath Tier 490.2%12.2%
OTIS Mock AIME 2024-2025100%86.7%
ProofBench95%9%
LMArena Math15191377
Omni-MATH—72.2%
MATH Level 5—97.8%
FrontierMath (Feb 2025 set)—27.2%
FrontierMath Erdős0%—
FrontierMath Tier 4 (v1)—6.3%

Knowledge Claude Fable 5 leads

Claude Fable 5: 62.3 (#22), GPT-5 Mini: 45.5 (#80)

BenchmarkClaude Fable 5GPT-5 Mini
GPQA Diamond85.9%75%
SimpleQA Verified70.7%21.6%
LMArena Expert15341377
Humanity's Last Exam—19.4%
MMLU-Pro—83.5%
Confabulations—13.3%
Vectara Hallucination Rate—12.9%
GPQA (HELM)—75.6%

Multimodal Claude Fable 5 leads

Claude Fable 5: 45.6 (#14), GPT-5 Mini: 35.0 (#80)

BenchmarkClaude Fable 5GPT-5 Mini
LMArena Vision13261202
VPCT—40.2%
Blueprint-Bench 238.6%—
Furniture Assembly35.8%—
LMArena Document1496—

Multilingual Claude Fable 5 leads

Claude Fable 5: 57.6 (#8), GPT-5 Mini: 49.1 (#131)

BenchmarkClaude Fable 5GPT-5 Mini
LMArena Non-English14831363
LMArena Chinese15461387
LMArena French15091385
LMArena German14861366
LMArena Japanese15071342
LMArena Korean14931306
LMArena Russian15071362
LMArena Spanish15031355

Instruction Following Claude Fable 5 leads

Claude Fable 5: 78.8 (#7), GPT-5 Mini: 76.4 (#43)

BenchmarkClaude Fable 5GPT-5 Mini
LMArena Instruction Following15031357
IFEval—92.7%

Long Context Claude Fable 5 leads

Claude Fable 5: 46.3 (#22), GPT-5 Mini: 41.9 (#127)

BenchmarkClaude Fable 5GPT-5 Mini
LMArena Longer Query15101355
Fiction.LiveBench—69.4%

Writing & Preference Claude Fable 5 leads

Claude Fable 5: 76.1 (#5), GPT-5 Mini: 55.4 (#143)

BenchmarkClaude Fable 5GPT-5 Mini
LMArena Text14911373
LMArena Creative Writing14941325
EQ-Bench Creative Writing19431313
LMArena Multi-Turn15051363
Short-Story Creative Writing—83.1%
WildBench—85.5%
EQ-Bench 41340—

Frequently asked questions

Is Claude Fable 5 better than GPT-5 Mini?

Claude Fable 5 is the stronger model overall, scoring 66.3 to 41.7 on the Noometry Index. GPT-5 Mini costs 29× 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 Mini?

GPT-5 Mini is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; Claude Fable 5 lists at $10 and $50.

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

Claude Fable 5 scores higher on coding benchmarks: 67.0 versus 40.0 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 Mini share?

39 benchmarks have published results for both models. Claude Fable 5 has 61 scored results on Noometry and GPT-5 Mini has 60.

Related comparisons

Go deeper