Noometry

Model comparison

Claude Fable 5 vs GPT-5.2

Claude Fable 5 is the stronger model overall, scoring 66.8 to 54.1 on the Noometry Index. GPT-5.2 costs 4.2× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.

Last verified . 47 shared benchmarks.

Claude Fable 5 Anthropic

66.8

Rank #5 Confirmed

GPT-5.2 OpenAI

54.1

Rank #34 Confirmed

Summary

  • They share 47 benchmarks with published results for both. Claude Fable 5 scores higher in 9 categories and GPT-5.2 in 1 category; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Fable 5 leads 88.5 to 60.0.
  • The biggest single-benchmark swing is ProofBench: 95% for Claude Fable 5 and 15% for GPT-5.2.
  • GPT-5.2 is cheaper at $1.75 / $14 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-5.2
ProviderAnthropicOpenAI
Noometry Index66.854.1
Released2026-06-072025-12-11
WeightsProprietaryProprietary
Context window1M400K
Max output128K128K
Input $ / M tokens$10$1.75
Output $ / M tokens$50$14
Results tracked6267

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-5.2: 51.6 (#37)

BenchmarkClaude Fable 5GPT-5.2
LMArena WebDev16251416
GSO78.4%27.4%
WeirdML91.9%72.2%
LMArena Coding15191447
ALE-Bench2,0411,294
SWE-bench Verified—73.8%
DeepSWE69.9%—
FrontierCode53.5%—
SWE-bench Verified (bash only)—72.8%
SWE-bench Multilingual—66.7%
FrontierSWE47%—
SciCode61%—
MirrorCode63.9%—
AlgoTune—2.05

Agentic & Tool Use Claude Fable 5 leads

Claude Fable 5: 54.0 (#2), GPT-5.2: 40.2 (#24)

BenchmarkClaude Fable 5GPT-5.2
Remote Labor Index16.1%2.5%
τ²-bench Banking39.7%32.2%
LMArena Search12301207
Vending-Bench 25,6803,591
Terminal-Bench—64.9%
APEX-Agents63.6%—
Berkeley Function Calling Leaderboard—55.9%
GDPval—49.7%
τ²-bench Airline—83%
τ²-bench Retail—81.6%
τ²-bench Telecom—89.7%
DeepResearch Bench—41.1%
PostTrainBench41.8%—
GBAEval74.5%—
GDP.pdf30%—
METR Time Horizons—75.3%

Reasoning Claude Fable 5 leads

Claude Fable 5: 76.8 (#6), GPT-5.2: 50.2 (#35)

BenchmarkClaude Fable 5GPT-5.2
ARC-AGI-289.2%52.9%
SimpleBench81.9%45.8%
Kagi LLM Benchmark91.4%73.3%
NYT Connections (extended)92.7%83.6%
ARC-AGI-198.5%86.2%
Chess Puzzles41%49%
EnigmaEval39.3%10.4%
EBR-Bench39.5%23%
LMArena Hard Prompts15081445
Mystery Game Puzzles52%23%
DTBench98.4%90.9%
LMCA61.1%43.9%
Epoch Capabilities Index162.06153.45
CritPt28.6%—
Surface Evolver Bench95%—
Bench to the Future 30.13—
ForecastBench—60.1

Math Claude Fable 5 leads

Claude Fable 5: 88.5 (#5), GPT-5.2: 60.0 (#38)

BenchmarkClaude Fable 5GPT-5.2
FrontierMath (Tiers 1-3)87%67.4%
FrontierMath Tier 490.2%31.7%
OTIS Mock AIME 2024-2025100%96.1%
ProofBench95%15%
LMArena Math15191440
MathArena Final-Answer Competitions—72%
FrontierMath (Feb 2025 set)—40.7%
FrontierMath Erdős0%—
FrontierMath Tier 4 (v1)—18.8%

Knowledge Claude Fable 5 leads

Claude Fable 5: 62.2 (#25), GPT-5.2: 59.3 (#32)

BenchmarkClaude Fable 5GPT-5.2
GPQA Diamond85.9%91.4%
SimpleQA Verified70.7%37.1%
LMArena Expert15341445
Humanity's Last Exam—27.8%
Vectara Hallucination Rate—8.4%

Multimodal GPT-5.2 leads

Claude Fable 5: 45.3 (#17), GPT-5.2: 51.3 (#7)

BenchmarkClaude Fable 5GPT-5.2
LMArena Vision13241268
Furniture Assembly35.8%38.3%
LMArena Document14961405
VPCT—84%
Blueprint-Bench 238.6%—

Multilingual Claude Fable 5 leads

Claude Fable 5: 57.3 (#9), GPT-5.2: 53.4 (#67)

BenchmarkClaude Fable 5GPT-5.2
LMArena Non-English14811425
LMArena Chinese15431460
LMArena French15051455
LMArena German14861448
LMArena Japanese15061420
LMArena Korean14881392
LMArena Russian15041440
LMArena Spanish14981433

Instruction Following Claude Fable 5 leads

Claude Fable 5: 78.6 (#8), GPT-5.2: 74.7 (#89)

BenchmarkClaude Fable 5GPT-5.2
LMArena Instruction Following15021417

Long Context Claude Fable 5 leads

Claude Fable 5: 46.3 (#23), GPT-5.2: 44.0 (#78)

BenchmarkClaude Fable 5GPT-5.2
LMArena Longer Query15091428
CL-bench—18.2%

Writing & Preference Claude Fable 5 leads

Claude Fable 5: 75.9 (#5), GPT-5.2: 66.8 (#32)

BenchmarkClaude Fable 5GPT-5.2
LMArena Text14911439
LMArena Creative Writing14941401
EQ-Bench Creative Writing19431703
LMArena Multi-Turn15041458
EQ-Bench 41340—

Frequently asked questions

Is Claude Fable 5 better than GPT-5.2?

Claude Fable 5 is the stronger model overall, scoring 66.8 to 54.1 on the Noometry Index. GPT-5.2 costs 4.2× 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-5.2?

GPT-5.2 is cheaper. It lists at $1.75 per million input tokens and $14 per million output tokens; Claude Fable 5 lists at $10 and $50.

Is Claude Fable 5 or GPT-5.2 better for coding?

Claude Fable 5 scores higher on coding benchmarks: 70.6 versus 51.6 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-5.2 share?

47 benchmarks have published results for both models. Claude Fable 5 has 62 scored results on Noometry and GPT-5.2 has 67.

Related comparisons

Go deeper