Enter opens the highlighted result. Esc closes.

Claude Fable 5 vs GPT-6 Luna

Claude Fable 5 leads GPT-6 Luna on coding, 79.3 to 57.3 on the Vibe Coding Index, and GPT-6 Luna costs 100.0x less per output token ($0.50 vs $50.00 per million). Updated October 22, 2026; 92 benchmarks have a result for both.

Replace Claude Fable 5 Replace GPT-6 Luna
Claude Fable 5Anthropic
Coding
79.3
Overall
79.0
Output $/M
$50.00
89
GPT-6 LunaOpenAI
Coding
57.3
Overall
59.7
Output $/M
$0.50
3
vs boards won of 92 shared

Claude Fable 5 or GPT-6 Luna: which to pick

Pick Claude Fable 5 for coding: it scores 79.3 on the Vibe Coding Index against 57.3 for GPT-6 Luna.

Pick GPT-6 Luna for output tokens 100.0x cheaper ($0.50 vs $50.00 per million) and a larger context window (1.05M against 1M tokens).

Model AClaude Fable 5Anthropic79.3/1006 independent benchmarks$2.16 per solved taskModel BGPT-6 LunaOpenAI57.3/1005 independent benchmarksNo cost per solved task
Shared results
92
Claude Fable 5 only
35
GPT-6 Luna only
11
Like-for-like categories
8 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

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 79.3 from 6 benchmarks, GPT-6 Luna 57.3 from 5 benchmarks.
Widest category
Knowledge, 19.0 points apart on average over 6 shared benchmarks.
Widest single gap
Mystery game puzzles: Claude Fable 5 52.0% against GPT-6 Luna 7.0%, 45.0 points apart on a 0 to 100 scale.
Output price
Claude Fable 5 $50.00 against GPT-6 Luna $0.50 per million output tokens, 100.0x apart.
Context window
Claude Fable 5 takes 1M tokens, GPT-6 Luna 1.05M.

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-6 LunaTies
Coding150
Intelligence20
Agentic work120
Reasoning111
Math60
Knowledge60
Web design90
General282
All shared boards893
CodingLike-for-likeSix of these boards feed the Vibe Coding Index150
Coding benchmarks for Claude Fable 5 and GPT-6 Luna
BenchmarkClaude Fable 5GPT-6 LunaLeader
LiveBench coding98.3%84.5%Claude Fable 5
LMArena WebDev16241578Claude Fable 5
AA Coding Index76.5Not measuredOnly Claude Fable 5 measured
LiveCodeBench (Vals AI)89.8%Not measuredOnly Claude Fable 5 measured
SWE-bench Verified (Vals AI)95.0%Not measuredOnly Claude Fable 5 measured
Terminal-Bench 4 (Vals AI)41.4%13.6%Claude Fable 5
Vibe Code Bench (Vals AI)90.3%81.7%Claude Fable 5
Code migration (Vals AI)55.1%42.5%Claude Fable 5
ProgramBench (Vals AI)2.0%0.5%Claude Fable 5
IOI (Vals AI)Not measured55.6%Only GPT-6 Luna measured
Terminal-Bench 2.1 (Vals AI)80.5%73.0%Claude Fable 5
SWE-bench Multimodal (Vals AI)Not measured37.5%Only GPT-6 Luna measured
CyberBench (Vals AI)Not measured76.3%Only GPT-6 Luna measured
SciCode61.0%54.6%Claude Fable 5
Terminal-Bench Hard (Artificial Analysis run)62.9%Not measuredOnly Claude Fable 5 measured
FrontierCode53.5%42.4%Claude Fable 5
FrontierSWE47.0%Not measuredOnly Claude Fable 5 measured
GSO-Bench78.4%Not measuredOnly Claude Fable 5 measured
WeirdML91.9%Not measuredOnly Claude Fable 5 measured
MirrorCode63.9%Not measuredOnly Claude Fable 5 measured
ALE-Bench2041.31576.9Claude Fable 5
LMArena Text: coding15181437Claude Fable 5
LMArena Text: software and IT15131423Claude Fable 5
LMArena WebDev: React16311573Claude Fable 5
LMArena WebDev: HTML16511595Claude Fable 5
LMArena WebDev: from an image16231571Claude Fable 5
Neither model has a result on the other 13 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Fable 5 and GPT-6 Luna
BenchmarkClaude Fable 5GPT-6 LunaLeader
AA Intelligence Index49.638.1Claude Fable 5
Epoch Capabilities Index163.4156.8Claude Fable 5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index120
Agentic work benchmarks for Claude Fable 5 and GPT-6 Luna
BenchmarkClaude Fable 5GPT-6 LunaLeader
AA Agentic Index50.7Not measuredOnly Claude Fable 5 measured
Design Arena: agents building web apps12611191Claude Fable 5
Design Arena: agents building full-stack apps12801158Claude Fable 5
Design Arena: agents building mobile apps12641134Claude Fable 5
Design Arena: agents building Android apps1284Not measuredOnly Claude Fable 5 measured
Design Arena: agents building Godot games1292Not measuredOnly Claude Fable 5 measured
Design Arena: agents building games1285Not measuredOnly Claude Fable 5 measured
Design Arena: HTML slides1227Not measuredOnly Claude Fable 5 measured
Design Arena: PowerPoint slides1270Not measuredOnly Claude Fable 5 measured
LiveBench research86.9%43.5%Claude Fable 5
LiveBench browser92.0%72.0%Claude Fable 5
LiveBench long agentic53.2%48.1%Claude Fable 5
SREBench (Vals AI)Not measured2.7%Only GPT-6 Luna measured
Finance Agent (Vals AI)56.3%49.9%Claude Fable 5
Tax Agent Bench (Vals AI)38.3%19.9%Claude Fable 5
Legal Research Bench (Vals AI)49.5%30.3%Claude Fable 5
Harvey's Legal Agent Benchmark (Vals AI)Not measured4.2%Only GPT-6 Luna measured
Excel Modeling Benchmark (Vals AI)73.7%68.5%Claude Fable 5
BioMysteryBench (Vals AI)Not measured61.5%Only GPT-6 Luna measured
Terminal-Bench-Science (Vals AI)15.7%4.3%Claude Fable 5
Vals Science IndexNot measured28.4%Only GPT-6 Luna measured
τ²-Bench Telecom98.5%Not measuredOnly Claude Fable 5 measured
APEX-Agents63.6%44.3%Claude Fable 5
Remote Labor Index16.1%Not measuredOnly Claude Fable 5 measured
PostTrainBench41.8%Not measuredOnly Claude Fable 5 measured
SpireClimbNot measured0.0%Only GPT-6 Luna measured
Vending-Bench 2$5,680Not measuredOnly Claude Fable 5 measured
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 index111
Reasoning benchmarks for Claude Fable 5 and GPT-6 Luna
BenchmarkClaude Fable 5GPT-6 LunaLeader
GPQA Diamond93.2%Not measuredOnly Claude Fable 5 measured
LiveBench reasoning89.7%81.8%Claude Fable 5
MysteryMechanism (Vals AI)Not measured19.4%Only GPT-6 Luna measured
MMMU Pro (Vals AI)89.3%Not measuredOnly Claude Fable 5 measured
GPQA Diamond (Artificial Analysis run)92.6%Not measuredOnly Claude Fable 5 measured
Humanity's Last Exam (Artificial Analysis run)55.5%38.5%Claude Fable 5
GPQA Diamond (Epoch AI run)85.9%90.5%GPT-6 Luna
ARC-AGI98.5%86.7%Claude Fable 5
ARC-AGI-289.2%59.3%Claude Fable 5
SimpleBench81.9%Not measuredOnly Claude Fable 5 measured
Chess puzzles47.0%36.0%Claude Fable 5
Mystery game puzzles52.0%7.0%Claude Fable 5
EBR-bench39.5%Not measuredOnly Claude Fable 5 measured
LMArena Text: hard prompts15071410Claude Fable 5
LMArena Text: expert15341442Claude Fable 5
LMArena Text: hard prompts in English15091410Claude Fable 5
LMArena Vision: diagrams13571245Claude Fable 5
LMArena Vision: homework13611261Claude Fable 5
Kagi LLM Benchmark91.4%Not measuredOnly Claude Fable 5 measured
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-6 Luna
BenchmarkClaude Fable 5GPT-6 LunaLeader
OTIS Mock AIME100.0%98.9%Claude Fable 5
FrontierMath, tiers 1 to 387.0%78.9%Claude Fable 5
FrontierMath, tier 490.2%56.1%Claude Fable 5
ProofBench95.0%64.0%Claude Fable 5
LMArena Text: math15161409Claude Fable 5
LMArena Text: mathematical work15151427Claude Fable 5
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index60
Knowledge benchmarks for Claude Fable 5 and GPT-6 Luna
BenchmarkClaude Fable 5GPT-6 LunaLeader
MMLU Pro91.5%Not measuredOnly Claude Fable 5 measured
LegalBench (Vals AI)88.6%Not measuredOnly Claude Fable 5 measured
CorpFin (Vals AI)71.8%Not measuredOnly Claude Fable 5 measured
TaxEval (Vals AI)76.9%Not measuredOnly Claude Fable 5 measured
MortgageTax (Vals AI)68.9%Not measuredOnly Claude Fable 5 measured
MedCode (Vals AI)56.1%44.7%Claude Fable 5
SimpleQA Verified70.7%41.4%Claude Fable 5
LMArena Text: science15061386Claude Fable 5
LMArena Text: medicine and healthcare14801352Claude Fable 5
LMArena Text: legal and government14981400Claude Fable 5
LMArena Text: business and finance14801388Claude Fable 5
FACTS Benchmark SuiteNot measured63.3%Only GPT-6 Luna measured
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index90
Web design benchmarks for Claude Fable 5 and GPT-6 Luna
BenchmarkClaude Fable 5GPT-6 LunaLeader
Design Arena: websites12951271Claude Fable 5
Design Arena: UI components13161295Claude Fable 5
Design Arena: game dev13351257Claude Fable 5
Design Arena: data viz13041216Claude Fable 5
Design Arena: 3D13181218Claude Fable 5
Design Arena: all code categories13101270Claude Fable 5
Design Arena: SVG13021252Claude Fable 5
Design Arena: ASCII art13291153Claude Fable 5
LiveBench design84.7%82.5%Claude Fable 5
GeneralLike-for-likePublic boards, shown as published, kept out of the index282
General benchmarks for Claude Fable 5 and GPT-6 Luna
BenchmarkClaude Fable 5GPT-6 LunaLeader
Vals IndexNot measured52.3%Only GPT-6 Luna measured
LiveBench data analysis80.5%73.4%Claude Fable 5
Public Benefits Bench (Vals AI)70.4%57.6%Claude Fable 5
SAGE (Vals AI)51.9%48.1%Claude Fable 5
MedScribe (Vals AI)88.5%83.7%Claude Fable 5
Vals Multimodal Index74.2%Not measuredOnly Claude Fable 5 measured
IFBench63.5%Not measuredOnly Claude Fable 5 measured
Long context reasoning (AA-LCR)82.3%83.3%GPT-6 Luna
DTBench98.4%90.1%Claude Fable 5
LMCA61.2%44.5%Claude Fable 5
Surface Evolver Bench95.0%Not measuredOnly Claude Fable 5 measured
Furniture assembly35.8%44.2%GPT-6 Luna
LMArena Text14911389Claude Fable 5
LMArena Text: instruction following15021408Claude Fable 5
LMArena Text: creative writing14941363Claude Fable 5
LMArena Vision13251216Claude Fable 5
LMArena Text: English14981393Claude Fable 5
LMArena Text: non-English14821381Claude Fable 5
LMArena Text: Chinese15431427Claude Fable 5
LMArena Text: German14861376Claude Fable 5
LMArena Text: Japanese15041369Claude Fable 5
LMArena Text: Korean14871359Claude Fable 5
LMArena Text: French15051408Claude Fable 5
LMArena Text: Spanish14981391Claude Fable 5
LMArena Text: Russian15031392Claude Fable 5
LMArena Text: Polish14941383Claude Fable 5
LMArena Text: multi-turn15041392Claude Fable 5
LMArena Text: longer queries15101408Claude Fable 5
LMArena Text: writing and language15011384Claude Fable 5
LMArena Text: entertainment and media14821364Claude Fable 5
LMArena Vision: English13231204Claude Fable 5
LMArena Vision: Chinese13731266Claude Fable 5
LMArena Vision: reading text13371225Claude Fable 5
LMArena Vision: humor1341Not measuredOnly Claude Fable 5 measured
LMArena Vision: creative writing13381205Claude Fable 5
LMArena Document1496Not measuredOnly Claude Fable 5 measured
Neither model has a result on the other 10 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-6 Luna
BenchmarkClaude Fable 5GPT-6 LunaLeader
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-6 Luna$0.0003Fits in one request

GPT-6 Luna costs less

Repository review

50K input + 3K output tokens

Claude Fable 5$0.650Fits in one request
GPT-6 Luna$0.0065Fits in one request

GPT-6 Luna costs less

Agent loop

200K input + 10K output tokens

Claude Fable 5$2.50Fits in one request
GPT-6 Luna$0.025Fits in one request

GPT-6 Luna 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-6 Luna
SpecificationAnthropic Claude Fable 5OpenAI GPT-6 Luna
MakerAnthropicOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedJune 9, 2026September 22, 2026
Context window1M1.05M
Input $/Mtok$10.00$0.10
Output $/Mtok$50.00$0.50
Coding index79.357.3
Independent measurements behind it65
Cost per solved task$2.16Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Fable 5 better than GPT-6 Luna for coding?

Pick Claude Fable 5 for coding: it scores 79.3 on the Vibe Coding Index against 57.3 for GPT-6 Luna. Pick GPT-6 Luna for output tokens 100.0x cheaper ($0.50 vs $50.00 per million) and a larger context window (1.05M against 1M tokens).

Which is cheaper, Claude Fable 5 or GPT-6 Luna?

Claude Fable 5 costs $10.00 per million input tokens and $50.00 per million output tokens; GPT-6 Luna costs $0.10 and $0.50. Cost per solved task is known for Claude Fable 5 only.

Which has the bigger context window, Claude Fable 5 or GPT-6 Luna?

GPT-6 Luna, with 1.05M tokens against 1M.

How many benchmarks is the Claude Fable 5 vs GPT-6 Luna comparison based on?

92 benchmarks have a result for both models as of October 22, 2026. Claude Fable 5's coding index rests on 6 independent benchmarks and GPT-6 Luna's on 5. 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-6-luna" title="Claude Fable 5 vs GPT-6 Luna, 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-6-luna">LLMBenchmark.ai, Claude Fable 5 vs GPT-6 Luna</a></p>