LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Fable 5 vs GPT-5.2

Updated October 21, 2026. 93 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Fable 5 Replace GPT-5.2
Claude Fable 5Anthropic
Coding
82.1
Overall
49.6
Output $/M
$50.00
88
GPT-5.2OpenAI
Coding
58.9
Overall
30.4
Output $/M
$14.00
5
vs boards won of 93 shared

Decision reading

Pick Claude Fable 5 for coding: it scores 82.1 on the Vibe Coding Index against 58.9 for GPT-5.2.

Pick GPT-5.2 when output tokens cost 3.6x less, or when a solved task costs $1.91 against $2.16.

Model AClaude Fable 5Anthropic82.1/1002 independent benchmarks$2.16 per solved taskModel BGPT-5.2OpenAI58.9/1002 independent benchmarks$1.91 per solved task
Shared results
93
Claude Fable 5 only
33
GPT-5.2 only
18
Like-for-like categories
8 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
Claude Fable 5 82.1 from 2 benchmarks, GPT-5.2 58.9 from 2 benchmarks.
Widest category
Math, 31.2 points apart on average over 6 shared benchmarks.
Widest single gap
ProofBench: Claude Fable 5 95.0% against GPT-5.2 15.0%, 80.0 points apart on a 0 to 100 scale.
Output price
Claude Fable 5 $50.00 against GPT-5.2 $14.00 per million output tokens, 3.6x apart.
Context window
Claude Fable 5 takes 1M tokens, GPT-5.2 400K.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryClaude Fable 5BarsGPT-5.2Ties
Coding110
Intelligence20
Agentic work80
Reasoning142
Math60
Knowledge110
Web design80
General283
All shared boards885
CodingLike-for-likeFour of these boards feed the Vibe Coding Index110
Coding benchmarks for Claude Fable 5 and GPT-5.2
BenchmarkClaude Fable 5GPT-5.2Leader
SWE-bench VerifiedNot measured72.8%Only GPT-5.2 measured
SWE-bench MultilingualNot measured66.7%Only GPT-5.2 measured
LiveBench coding98.3%Not measuredOnly Claude Fable 5 measured
LMArena WebDev16241417Claude Fable 5
AA Coding Index76.5Not measuredOnly Claude Fable 5 measured
LiveCodeBench (Vals AI)89.8%85.4%Claude Fable 5
SWE-bench Verified (Vals AI)95.0%75.8%Claude Fable 5
Terminal-Bench 4 (Vals AI)41.4%Not measuredOnly Claude Fable 5 measured
Vibe Code Bench (Vals AI)90.3%53.5%Claude Fable 5
Code migration (Vals AI)55.1%Not measuredOnly Claude Fable 5 measured
ProgramBench (Vals AI)2.0%Not measuredOnly Claude Fable 5 measured
Terminal-Bench 2.1 (Vals AI)80.5%Not measuredOnly Claude Fable 5 measured
LiveCodeBench (Artificial Analysis run)Not measured89.4%Only GPT-5.2 measured
SciCode61.0%Not measuredOnly Claude Fable 5 measured
Terminal-Bench Hard (Artificial Analysis run)62.9%47.0%Claude Fable 5
Terminal-BenchNot measured64.9%Only GPT-5.2 measured
FrontierCode53.5%Not measuredOnly Claude Fable 5 measured
FrontierSWE47.0%Not measuredOnly Claude Fable 5 measured
GSO-Bench78.4%27.5%Claude Fable 5
WeirdML91.9%72.2%Claude Fable 5
MirrorCode63.9%Not measuredOnly Claude Fable 5 measured
ALE-Bench2041.31293.5Claude Fable 5
LMArena Text: coding15181442Claude Fable 5
LMArena Text: software and IT15131434Claude Fable 5
LMArena WebDev: React1631Not measuredOnly Claude Fable 5 measured
LMArena WebDev: HTML16511427Claude Fable 5
LMArena WebDev: from an image1623Not measuredOnly Claude Fable 5 measured
Neither model has a result on the other 11 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Fable 5 and GPT-5.2
BenchmarkClaude Fable 5GPT-5.2Leader
AA Intelligence Index49.630.4Claude Fable 5
Epoch Capabilities Index163.4153.7Claude Fable 5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index80
Agentic work benchmarks for Claude Fable 5 and GPT-5.2
BenchmarkClaude Fable 5GPT-5.2Leader
AA Agentic Index50.7Not measuredOnly Claude Fable 5 measured
Design Arena: agents building web apps12611086Claude Fable 5
Design Arena: agents building full-stack apps12801043Claude Fable 5
Design Arena: agents building mobile apps12641094Claude Fable 5
Design Arena: agents building Android apps12891064Claude Fable 5
Design Arena: agents building Godot games12921142Claude Fable 5
Design Arena: agents building games1285Not measuredOnly Claude Fable 5 measured
Design Arena: HTML slides1277Not measuredOnly Claude Fable 5 measured
Design Arena: PowerPoint slides1295Not measuredOnly Claude Fable 5 measured
LiveBench research86.9%Not measuredOnly Claude Fable 5 measured
LiveBench browser92.0%Not measuredOnly Claude Fable 5 measured
LiveBench long agentic53.2%Not measuredOnly Claude Fable 5 measured
Finance Agent (Vals AI)56.3%Not measuredOnly Claude Fable 5 measured
Tax Agent Bench (Vals AI)38.3%Not measuredOnly Claude Fable 5 measured
Legal Research Bench (Vals AI)49.5%Not measuredOnly Claude Fable 5 measured
Excel Modeling Benchmark (Vals AI)73.7%Not measuredOnly Claude Fable 5 measured
Terminal-Bench-Science (Vals AI)15.7%Not measuredOnly Claude Fable 5 measured
τ²-Bench Telecom98.5%84.8%Claude Fable 5
APEX-Agents63.6%Not measuredOnly Claude Fable 5 measured
METR time horizonsNot measured75.3%Only GPT-5.2 measured
Remote Labor Index16.1%2.5%Claude Fable 5
GDPvalNot measured49.7%Only GPT-5.2 measured
DeepResearch BenchNot measured41.1%Only GPT-5.2 measured
PostTrainBench41.8%Not measuredOnly Claude Fable 5 measured
Vending-Bench 2$5,680$3,591Claude Fable 5
LMArena Search1229Not measuredOnly Claude Fable 5 measured
Neither model has a result on the other 13 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index142
Reasoning benchmarks for Claude Fable 5 and GPT-5.2
BenchmarkClaude Fable 5GPT-5.2Leader
GPQA Diamond93.2%91.7%Claude Fable 5
LiveBench reasoning89.7%Not measuredOnly Claude Fable 5 measured
MMMU Pro (Vals AI)89.3%86.7%Claude Fable 5
GPQA Diamond (Artificial Analysis run)92.6%90.3%Claude Fable 5
Humanity's Last Exam (Artificial Analysis run)55.5%37.7%Claude Fable 5
GPQA Diamond (Epoch AI run)85.9%91.4%GPT-5.2
ARC-AGI98.5%86.2%Claude Fable 5
ARC-AGI-289.2%52.9%Claude Fable 5
SimpleBench81.9%45.8%Claude Fable 5
Chess puzzles47.0%48.0%GPT-5.2
Mystery game puzzles52.0%23.0%Claude Fable 5
EBR-bench39.5%23.0%Claude Fable 5
VPCTNot measured84.0%Only GPT-5.2 measured
LMArena Text: hard prompts15071428Claude Fable 5
LMArena Text: expert15341445Claude Fable 5
LMArena Text: hard prompts in English15091431Claude Fable 5
LMArena Vision: diagrams13571265Claude Fable 5
LMArena Vision: homework13611276Claude Fable 5
Neither model has a result on the other 3 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for Claude Fable 5 and GPT-5.2
BenchmarkClaude Fable 5GPT-5.2Leader
AIMENot measured96.9%Only GPT-5.2 measured
MGSM (Vals AI)Not measured94.0%Only GPT-5.2 measured
AA Math IndexNot measured99.0Only GPT-5.2 measured
AIME 2025 (Artificial Analysis run)Not measured99.0%Only GPT-5.2 measured
OTIS Mock AIME100.0%96.1%Claude Fable 5
FrontierMath, tiers 1 to 387.0%67.4%Claude Fable 5
FrontierMath, tier 490.2%31.7%Claude Fable 5
ProofBench95.0%15.0%Claude Fable 5
LMArena Text: math15161440Claude Fable 5
LMArena Text: mathematical work15151442Claude Fable 5
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index110
Knowledge benchmarks for Claude Fable 5 and GPT-5.2
BenchmarkClaude Fable 5GPT-5.2Leader
MMLU Pro91.5%86.2%Claude Fable 5
LegalBench (Vals AI)88.6%82.8%Claude Fable 5
CaseLaw (Vals AI)Not measured66.0%Only GPT-5.2 measured
CorpFin (Vals AI)71.8%65.9%Claude Fable 5
TaxEval (Vals AI)76.9%75.8%Claude Fable 5
MortgageTax (Vals AI)68.9%67.1%Claude Fable 5
MedQA (Vals AI)Not measured94.1%Only GPT-5.2 measured
MedCode (Vals AI)56.1%49.8%Claude Fable 5
MMLU Pro (Artificial Analysis run)Not measured87.4%Only GPT-5.2 measured
SimpleQA Verified70.7%37.1%Claude Fable 5
LMArena Text: science15061425Claude Fable 5
LMArena Text: medicine and healthcare14801425Claude Fable 5
LMArena Text: legal and government14981427Claude Fable 5
LMArena Text: business and finance14801414Claude Fable 5
Neither model has a result on the other 3 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for Claude Fable 5 and GPT-5.2
BenchmarkClaude Fable 5GPT-5.2Leader
Design Arena: websites12961196Claude Fable 5
Design Arena: UI components13181190Claude Fable 5
Design Arena: game dev13361196Claude Fable 5
Design Arena: data viz13041202Claude Fable 5
Design Arena: 3D13191079Claude Fable 5
Design Arena: all code categories13101171Claude Fable 5
Design Arena: SVG13021137Claude Fable 5
Design Arena: ASCII art13281153Claude Fable 5
LiveBench design84.7%Not measuredOnly Claude Fable 5 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index283
General benchmarks for Claude Fable 5 and GPT-5.2
BenchmarkClaude Fable 5GPT-5.2Leader
LiveBench data analysis80.5%Not measuredOnly Claude Fable 5 measured
Public Benefits Bench (Vals AI)70.4%Not measuredOnly Claude Fable 5 measured
SAGE (Vals AI)51.9%49.3%Claude Fable 5
MedScribe (Vals AI)88.5%84.4%Claude Fable 5
Vals Multimodal Index74.2%Not measuredOnly Claude Fable 5 measured
IFBench63.5%75.4%GPT-5.2
Long context reasoning (AA-LCR)82.3%82.7%GPT-5.2
DTBench98.4%90.9%Claude Fable 5
LMCA61.2%43.9%Claude Fable 5
CL-benchNot measured18.2%Only GPT-5.2 measured
Surface Evolver Bench95.0%Not measuredOnly Claude Fable 5 measured
Furniture assembly35.8%38.3%GPT-5.2
LMArena Text14911416Claude Fable 5
LMArena Text: instruction following15021409Claude Fable 5
LMArena Text: creative writing14941376Claude Fable 5
LMArena Vision13251246Claude Fable 5
LMArena Text: English14981422Claude Fable 5
LMArena Text: non-English14821405Claude Fable 5
LMArena Text: Chinese15431447Claude Fable 5
LMArena Text: German14861444Claude Fable 5
LMArena Text: Japanese15041420Claude Fable 5
LMArena Text: Korean14871374Claude Fable 5
LMArena Text: French15051454Claude Fable 5
LMArena Text: Spanish14981413Claude Fable 5
LMArena Text: Russian15031415Claude Fable 5
LMArena Text: Polish14941426Claude Fable 5
LMArena Text: multi-turn15041419Claude Fable 5
LMArena Text: longer queries15101413Claude Fable 5
LMArena Text: writing and language15011392Claude Fable 5
LMArena Text: entertainment and media14821378Claude Fable 5
LMArena Vision: English13231243Claude Fable 5
LMArena Vision: Chinese13731305Claude Fable 5
LMArena Vision: reading text13371257Claude Fable 5
LMArena Vision: humor13411227Claude Fable 5
LMArena Vision: captioningNot measured1267Only GPT-5.2 measured
LMArena Vision: recognizing thingsNot measured1232Only GPT-5.2 measured
LMArena Vision: creative writing13381225Claude Fable 5
LMArena Document14961405Claude Fable 5
Neither model has a result on the other 8 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Fable 5 and GPT-5.2
BenchmarkClaude Fable 5GPT-5.2Leader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Claude Fable 5$0.035Fits in one request
GPT-5.2$0.0088Fits in one request

GPT-5.2 costs less

Repository review

50K input + 3K output tokens

Claude Fable 5$0.650Fits in one request
GPT-5.2$0.130Fits in one request

GPT-5.2 costs less

Agent loop

200K input + 10K output tokens

Claude Fable 5$2.50Fits in one request
GPT-5.2$0.490Fits in one request

GPT-5.2 costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Claude Fable 5 and GPT-5.2
SpecificationAnthropic Claude Fable 5OpenAI GPT-5.2
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedJune 9, 2026December 10, 2025
Context window1M400K
Input $/Mtok$10.00$1.75
Output $/Mtok$50.00$14.00
Coding index82.158.9
Independent measurements behind it22
Cost per solved task$2.16$1.91
SourceOpenRouter listingOpenRouter listing

Questions

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

Pick Claude Fable 5 for coding: it scores 82.1 on the Vibe Coding Index against 58.9 for GPT-5.2. Pick GPT-5.2 when output tokens cost 3.6x less, or when a solved task costs $1.91 against $2.16.

Which is cheaper, Claude Fable 5 or GPT-5.2?

Claude Fable 5 costs $10.00 per million input tokens and $50.00 per million output tokens; GPT-5.2 costs $1.75 and $14.00. Per solved SWE-bench Verified task, Claude Fable 5 costs $2.16 and GPT-5.2 $1.91.

Which has the bigger context window, Claude Fable 5 or GPT-5.2?

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

How many benchmarks is the Claude Fable 5 vs GPT-5.2 comparison based on?

93 benchmarks have a result for both models as of October 21, 2026. Claude Fable 5's coding index rests on 2 independent benchmarks and GPT-5.2's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/claude-fable-5-vs-gpt-5-2" title="Claude Fable 5 vs GPT-5.2, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/claude-fable-5-vs-gpt-5-2">LLMBenchmark.ai, Claude Fable 5 vs GPT-5.2</a></p>