Noometry

Model comparison

Claude Fable 5.1 vs GPT-5.2

Claude Fable 5.1 is the stronger model overall, scoring 69.0 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 5.1's lead doesn't matter for your workload.

Last verified . 42 shared benchmarks.

Claude Fable 5.1 Anthropic

69.0

Rank #2 Confirmed

GPT-5.2 OpenAI

54.1

Rank #34 Confirmed

Summary

  • They share 42 benchmarks with published results for both. Claude Fable 5.1 scores higher in 10 categories and GPT-5.2 in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Fable 5.1 leads 89.6 to 60.0.
  • The biggest single-benchmark swing is ProofBench: 100% for Claude Fable 5.1 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 5.1.
  • Claude Fable 5.1 accepts more context: 1M tokens versus 400K.

Side by side

Claude Fable 5.1GPT-5.2
ProviderAnthropicOpenAI
Noometry Index69.054.1
Released2026-09-012025-12-11
WeightsProprietaryProprietary
Context window1M400K
Max output128K128K
Input $ / M tokens$10$1.75
Output $ / M tokens$50$14
Results tracked5267

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Claude Fable 5.1 leads

Claude Fable 5.1: 74.7 (#1), GPT-5.2: 51.6 (#37)

BenchmarkClaude Fable 5.1GPT-5.2
LMArena WebDev17441416
GSO88.2%27.4%
WeirdML92.9%72.2%
LMArena Coding15281447
ALE-Bench2,1431,294
SWE-bench Verified—73.8%
FrontierCode50.9%—
SWE-bench Verified (bash only)—72.8%
CursorBench51.8%—
SWE-bench Multilingual—66.7%
FrontierSWE56.3%—
SciCode63.1%—
MirrorCode73.3%—
AlgoTune—2.05

Agentic & Tool Use Claude Fable 5.1 leads

Claude Fable 5.1: 50.7 (#5), GPT-5.2: 40.2 (#24)

BenchmarkClaude Fable 5.1GPT-5.2
Remote Labor Index17.9%2.5%
Vending-Bench 25,4223,591
Terminal-Bench—64.9%
APEX-Agents68.6%—
Berkeley Function Calling Leaderboard—55.9%
GDPval—49.7%
τ²-bench Airline—83%
τ²-bench Banking—32.2%
τ²-bench Retail—81.6%
τ²-bench Telecom—89.7%
DeepResearch Bench—41.1%
GDP.pdf29.6%—
LMArena Search—1207
METR Time Horizons—75.3%

Reasoning Claude Fable 5.1 leads

Claude Fable 5.1: 76.7 (#7), GPT-5.2: 50.2 (#35)

BenchmarkClaude Fable 5.1GPT-5.2
ARC-AGI-290%52.9%
NYT Connections (extended)90%83.6%
ARC-AGI-197.5%86.2%
Chess Puzzles47%49%
EBR-Bench57.1%23%
LMArena Hard Prompts15261445
Mystery Game Puzzles58%23%
DTBench97.6%90.9%
LMCA65.5%43.9%
Epoch Capabilities Index164.7153.45
SimpleBench—45.8%
Kagi LLM Benchmark—73.3%
CritPt31.1%—
EnigmaEval—10.4%
ForecastBench—60.1

Math Claude Fable 5.1 leads

Claude Fable 5.1: 89.6 (#4), GPT-5.2: 60.0 (#38)

BenchmarkClaude Fable 5.1GPT-5.2
FrontierMath (Tiers 1-3)90.2%67.4%
FrontierMath Tier 487.8%31.7%
OTIS Mock AIME 2024-2025100%96.1%
ProofBench100%15%
LMArena Math15251440
MathArena Final-Answer Competitions—72%
FrontierMath (Feb 2025 set)—40.7%
FrontierMath Erdős0%—
FrontierMath Tier 4 (v1)—18.8%

Knowledge Claude Fable 5.1 leads

Claude Fable 5.1: 69.6 (#6), GPT-5.2: 59.3 (#32)

BenchmarkClaude Fable 5.1GPT-5.2
Humanity's Last Exam46.5%27.8%
SimpleQA Verified70.8%37.1%
LMArena Expert15351445
GPQA Diamond—91.4%
Vectara Hallucination Rate—8.4%

Multimodal Claude Fable 5.1 leads

Claude Fable 5.1: 53.9 (#4), GPT-5.2: 51.3 (#7)

BenchmarkClaude Fable 5.1GPT-5.2
LMArena Vision13181268
Furniture Assembly70%38.3%
LMArena Document15131405
VPCT—84%
Blueprint-Bench 241.9%—

Multilingual Claude Fable 5.1 leads

Claude Fable 5.1: 59.1 (#3), GPT-5.2: 53.4 (#67)

BenchmarkClaude Fable 5.1GPT-5.2
LMArena Non-English15071425
LMArena Chinese15861460
LMArena French15251455
LMArena German15001448
LMArena Japanese15431420
LMArena Korean15341392
LMArena Russian15211440
LMArena Spanish15161433

Instruction Following Claude Fable 5.1 leads

Claude Fable 5.1: 79.2 (#6), GPT-5.2: 74.7 (#89)

BenchmarkClaude Fable 5.1GPT-5.2
LMArena Instruction Following15171417

Long Context Claude Fable 5.1 leads

Claude Fable 5.1: 46.7 (#20), GPT-5.2: 44.0 (#78)

BenchmarkClaude Fable 5.1GPT-5.2
LMArena Longer Query15221428
CL-bench—18.2%

Writing & Preference Claude Fable 5.1 leads

Claude Fable 5.1: 79.2 (#2), GPT-5.2: 66.8 (#32)

BenchmarkClaude Fable 5.1GPT-5.2
LMArena Text15101439
LMArena Creative Writing15071401
EQ-Bench Creative Writing21621703
LMArena Multi-Turn14921458

Frequently asked questions

Is Claude Fable 5.1 better than GPT-5.2?

Claude Fable 5.1 is the stronger model overall, scoring 69.0 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 5.1's lead doesn't matter for your workload.

Which is cheaper, Claude Fable 5.1 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 5.1 lists at $10 and $50.

Is Claude Fable 5.1 or GPT-5.2 better for coding?

Claude Fable 5.1 scores higher on coding benchmarks: 74.7 versus 51.6 in the Noometry coding category.

Which has the bigger context window?

Claude Fable 5.1 does, with 1M tokens against 400K.

How many benchmarks do Claude Fable 5.1 and GPT-5.2 share?

42 benchmarks have published results for both models. Claude Fable 5.1 has 52 scored results on Noometry and GPT-5.2 has 67.

Related comparisons

Go deeper