AnthropicOpenAILLM matchup

Claude Fable 5.1vs.GPT-6 Luna

Which one is better?

Claude Fable 5.1 performs better than GPT-6 Luna, but costs 100 times as much.

Fable 5.1 ahead

IntelligenceOverall index, 100 points = average

123.8

Claude Fable 5.1

Rank 3

96.3

GPT-6 Luna

Rank 35

about as fast

SpeedTokens per second

Claude Fable 5.1

101

GPT-6 Luna

GPT-6 Luna cheaper

Price$ per 1M tokens

$20

Claude Fable 5.1

$0.20

GPT-6 Luna

about as popular

Popularity0 to 100

Claude Fable 5.1

Rank 18 of 785

GPT-6 Luna

Rank 30 of 785

Above 272,000 tokens of context, GPT-6 Luna costs more: $0.20 input and $0.75 output per 1M tokens.

Choose Claude Fable 5.1 for

LegalProductivityKnowledgeMultimodalGeneralHealthCodingMathematicsFinanceCybersecurityReasoningAgents

Choose GPT-6 Luna for

No clear advantage

Where is the difference?

Strengths at a glance

Fable 5.1GPT-6 LunaMedian of all ranked models

CodingFable 5.1 ahead

Fable 5.1122.8Rank 5

GPT-6 Luna97.5Rank 35

Median of ranked models84.1

95 % range: Fable 5.1 117.1 to 128.5, GPT-6 Luna 94.5 to 100.5.

AreaFable 5.1GPT-6 Luna

The same values and verdicts as the bars below. In the close-up the net starts at 80 points, just below the weaker model's lowest value; the reference group average is 100.

Fable 5.1 is ahead in 10 of 10 areas, GPT-6 Luna in none.

Fable 5.1 ahead: 10

Areas in the overall index

KnowledgeFable 5.1 +38127.2 to 89.2

MultimodalFable 5.1 +28120.2 to 92.0

GeneralFable 5.1 +28122.5 to 94.4

CodingFable 5.1 +25122.8 to 97.5

MathematicsFable 5.1 +25130.2 to 105.5

ReasoningFable 5.1 +18116.3 to 97.8

AgentsFable 5.1 +15114.5 to 99.5

Specialist fields

LegalFable 5.1 +39129.7 to 90.7

HealthFable 5.1 +28122.9 to 95.2

FinanceFable 5.1 +23121.1 to 98.3

Bar length shows the gap in index points (full width 15 points, one standard deviation of the reference group). Solid means clearly ahead, hatched not certain yet, a thin grey bar level.

Show 4 more areas that do not count toward the overall index

ProductivityFable 5.1 +38128.8 to 90.5

CybersecurityFable 5.1 +22123.5 to 101.8

Searchonly GPT-6 Luna has a score

Educationonly GPT-6 Luna has a score

Bar length shows the gap in index points (full width 15 points, one standard deviation of the reference group). Solid means clearly ahead, hatched not certain yet, a thin grey bar level.

Claude Fable 5.1 vs. GPT-6 Luna at the same effort

Both models measured at the same reasoning efforts. This shows whether a lead comes from the model or only from more compute.

lowFable 5.1 ahead

Fable 5.1 113.1 vs. GPT-6 Luna 65.2 · Gap 47.2 · Test series 10

mediumFable 5.1 ahead

Fable 5.1 117.2 vs. GPT-6 Luna 82.4 · Gap 33.4 · Test series 10

highFable 5.1 ahead

Fable 5.1 120.7 vs. GPT-6 Luna 87.1 · Gap 31.2 · Test series 10

xhighFable 5.1 ahead

Fable 5.1 123.9 vs. GPT-6 Luna 90.6 · Gap 30.9 · Test series 10

maxFable 5.1 ahead

Fable 5.1 123.8 vs. GPT-6 Luna 96.3 · Gap 22.5 · Test series 12

Overall index (max vs. max)Fable 5.1 ahead

Fable 5.1 123.8 vs. GPT-6 Luna 96.3

Effort	Fable 5.1	GPT-6 Luna	Gap	Verdict	Test series
low	113.1	65.2	47.2	Fable 5.1 ahead	10
medium	117.2	82.4	33.4	Fable 5.1 ahead	10
high	120.7	87.1	31.2	Fable 5.1 ahead	10
xhigh	123.9	90.6	30.9	Fable 5.1 ahead	10
max	123.8	96.3	22.5	Fable 5.1 ahead	12
Overall index (max vs. max)	123.8	96.3	27.6	Fable 5.1 ahead

Gap and verdict compare only the Artificial Analysis test series in which both models are measured at that effort. Tied below 3 points, ahead only beyond two standard errors. The single values rest on all test series of each model, so their difference can deviate from the gap.

Which model for which task?

Everyday tasks, translated from the area values above. Each row names the values it rests on.

TaskBetter choicebased on

Writing and debugging codeFable 5.1Coding 122.8 to 97.5

Maths and data analysisFable 5.1Mathematics 130.2 to 105.5, Reasoning 116.3 to 97.8

Facts and researchFable 5.1Knowledge 127.2 to 89.2, Search without a score for Fable 5.1

Agents and workflowsFable 5.1Agents 114.5 to 99.5

Fast chat repliesabout the same88 to 101 tokens per second

Security analysisFable 5.1Cybersecurity 123.5 to 101.8

Many requests on a small budgetGPT-6 Luna$20 to $0.20 per 1M tokens

Finance, legal and medical textsFable 5.1Finance 121.1 to 98.3, Legal 129.7 to 90.7, Health 122.9 to 95.2

Images, screenshots and PDFsFable 5.1Multimodal 120.2 to 92.0

See for yourself: same task, one attempt

The same prompt for both models. We show the latest attempt without fixes; it does not count toward the overall index.

Pelican on a bicycle

Prompt

Generate an SVG of a pelican riding a bicycle

Task origin: Simon Willison

Claude Fable 5.1

Sep 7, 2026 · 27 s · $0.11

Test details

Run date: Sep 7, 2026
API provider: openrouter
Requested API model: anthropic/claude-fable-5.1
Reasoning setting: high
Token limit including reasoning: 8,192 tokens
Output tokens: 2,198 tokens
Cost of the attempt: $0.1102
Response time: 27 s
API model reported in response: anthropic/claude-fable-5.1
Pinned endpoint: Anthropic | anthropic/claude-fable-5.1-20260831
Temperature: Provider default
Test protocol: community-visual-tests-v1
Technical checks: Passed, not a quality rating

Visually reviewed. This individual test does not establish overall model quality.

GPT-6 Luna

Oct 1, 2026 · 47 s · $0.0022

Test details

Run date: Oct 1, 2026
API provider: openrouter
Requested API model: openai/gpt-6-luna
Reasoning setting: high
Token limit including reasoning: 8,192 tokens
Output tokens: 4,493 tokens
Cost of the attempt: $0.0022
Response time: 46.7 s
API model reported in response: openai/gpt-6-luna
Pinned endpoint: OpenAI | openai/gpt-6-luna-20260922
Temperature: Provider default
Test protocol: community-visual-tests-v1
Technical checks: Passed, not a quality rating

Visually reviewed. This individual test does not establish overall model quality.

SVG short test

One SVG task with the same fixed settings for every model, without hidden thinking.

Prompt

Return only one standalone SVG of a pelican riding a bicycle. Use viewBox="0 0 800 600", simple shapes, two clearly visible wheels and a recognizable pelican with a long beak. At most 30 SVG elements and 1800 characters. No Markdown, explanations, comments, scripts, animation, CSS or external resources.

Claude Fable 5.1

Unavailable in this round

GPT-6 Luna

Unavailable in this round

Claude Fable 5.1 and GPT-6 Luna in the overall index

Every model with a place in the overall index, both models of this matchup highlighted. You can add or hide other models.

Overall index (Gradually Meta-Score v4)

20 of 92 models

4 models in this view are measured at a lower reasoning effort than max in the overall index. Dashed column: lower reasoning effort than the top.

Claude Opus 5.5max126.1

Gemini 4 Carbonhigh125.8

Claude Fable 5.1max123.8

Claude Sonnet 5.5max122.8

Gemini 4 Argonhigh122.3

GPT-6 Astramax121.3

GPT-6.1 Solmax119.2

Muse Wonder Fullmax118.3

Claude Opus 5max117.2

Muse Wondermax113.4

Kimi K3.1 Promax112.9

Claude Fable 5max112.5

GPT-6 Solmax110.5

GPT-5.6 Solmax108.7

Muse Spark 1.3max107.4

Gemini 3.7 Flashhigh107.1

DeepSeek V4.1 Flash 1017max106.6

Gemini 3.8 Flashhigh106.5

GPT-6.1 Terramax105.3

GPT-6 Lunamax96.3

Claude Opus 5.5

Gemini 4 Carbon

Claude Fable 5.1

Claude Sonnet 5.5

Gemini 4 Argon

GPT-6 Astra

GPT-6.1 Sol

Muse Wonder Full

Claude Opus 5

Muse Wonder

Kimi K3.1 Pro

Claude Fable 5

GPT-6 Sol

GPT-5.6 Sol

Muse Spark 1.3

Gemini 3.7 Flash

DeepSeek V4.1 Flash 1017

Gemini 3.8 Flash

GPT-6.1 Terra

GPT-6 Luna

Popularity compared

How often the models are searched for, used and mentioned, on a scale from 0 to 100.

Both are about as popular: Claude Fable 5.1 64, GPT-6 Luna 60 out of 100.

Over time

Weekly values from October 18, 2026 to November 7, 2026

Claude Fable 5.1GPT-6 Luna

All data side by side

The better value is bold. For the overall index only when the gap is clear.

Metric	Claude Fable 5.1	GPT-6 Luna
Intelligence
Overall indexpoints, 100 = reference group average, higher is better	123.8	96.3
Rank	Rank 3 of 92	Rank 35 of 92
Price per 1M tokens
Inputwhat you send	$10	$0.10above 272,000 tokens: $0.20
Outputwhat the model writes	$50	$0.50above 272,000 tokens: $0.75
Cost per task (own tests)average of 3 original-protocol tasks both models passed (SVG short test not included)	$0.19	$0.003
Speed
Tokens per second	88	101
Popularity
Popularitysearch, usage and mentions, 0 to 100	64Rank 18 of 785	60Rank 30 of 785
Technical
Context windowhow much text the model reads at once	1 M tokens≈ 1,500 A4 pages	1.05 M tokens≈ 1,580 A4 pages
Knowledge cutoff	June 2026	May 18, 2026
Released	Sep 1, 2026	Sep 22, 2026
Availability	Active	Active
Open weights	no	no

Prices without caching or batch discounts · Page count as a rule of thumb from Artificial Analysis

Is there a better choice?

As cheap as GPT-6 LunaClaude Haiku 5.5

Overall index 103.4, rank 20$0.10 input and $0.50 output per 1M tokens

Fable 5.1 vs. Claude Haiku 5.5

Best model in the overall indexClaude Opus 5.5

Overall index 126.1, rank 1$4 input and $20 output per 1M tokens

Fable 5.1 vs. Claude Opus 5.5

Shared benchmarks

Single results from the same benchmark version, task and metric. A value is bold only with the same test setup and a clear gap.

A: Claude Fable 5.1B: GPT-6 Luna

Code MigrationOverall · higher is betterTest setup not documented as identical54.6%42.6%Vals AIAs of 10/29/2026

CyberBench v1.1Overall · higher is betterTest setup not documented as identical70.4%76.3%Vals AIAs of 11/05/2026

EMBOverall · higher is betterTest setup not documented as identical76.7%68.5%Vals AIAs of 10/20/2026

EMB v1.1Overall · higher is betterTest setup not documented as identical76.7%70.0%Vals AIAs of 11/05/2026

Finance Agent (v2)Overall · higher is betterTest setup not documented as identical58.9%49.9%Vals AIAs of 10/29/2026

ImmigrationOverall · higher is betterTest setup not documented as identical75.4%62.5%Vals AIAs of 10/28/2026

IOIOverall · higher is betterTest setup not documented as identical90.8%55.6%Vals AIAs of 10/29/2026

Legal Research BenchOverall · All-pass · higher is betterTest setup not documented as identical55.3%30.3%Vals AIAs of 11/05/2026

LMArena Code Arena WebDevOverall · higher is better1,7461,579LMArenaAs of 10/28/2026

LMArena Text, Style ControlOverall · higher is better1,5041,441LMArenaAs of 10/28/2026

Show 54 more benchmarks

LMArena Vision, Style ControlOverall · higher is better1,2881,240LMArenaAs of 10/19/2026

MedCodeOverall · higher is betterTest setup not documented as identical53.5%44.7%Vals AIAs of 10/29/2026

MedScribeOverall · higher is betterTest setup not documented as identical91.3%83.7%Vals AIAs of 10/29/2026

MysteryMechanismOverall · higher is betterTest setup not documented as identical47.7%19.4%Vals AIAs of 10/29/2026

ProgramBenchOverall · higher is betterTest setup not documented as identical7.0%0.5%Vals AIAs of 11/05/2026

ProofBench v1.1Overall · higher is betterTest setup not documented as identical100%64%Vals AIAs of 10/29/2026

Public Benefits Bench v1.1Overall · higher is betterTest setup not documented as identical74.9%57.6%Vals AIAs of 10/12/2026

SRE BenchOverall · higher is betterTest setup not documented as identical22.9%2.7%Vals AIAs of 11/05/2026

SWE-bench MultimodalOverall · higher is betterTest setup not documented as identical61.3%37.5%Vals AIAs of 11/05/2026

Tax Agent BenchOverall · higher is betterTest setup not documented as identical49.2%19.9%Vals AIAs of 11/05/2026

Terminal-Bench 4.0Overall · higher is betterTest setup not documented as identical58.1%13.6%Vals AIAs of 11/05/2026

Terminal-Bench-ScienceOverall · higher is betterTest setup not documented as identical40.0%4.3%Vals AIAs of 11/05/2026

Vibe Code Bench v1.1Overall · higher is betterTest setup not documented as identical90.3%81.6%Vals AIAs of 11/05/2026

Code MigrationCLI · higher is betterTest setup not documented as identical52.8%37.2%Vals AIAs of 10/29/2026

CyberBench v1.1Patch · higher is betterTest setup not documented as identical87.5%87.5%Vals AIAs of 11/05/2026

EMBComps · higher is betterTest setup not documented as identical82.2%70.5%Vals AIAs of 10/20/2026

EMB v1.1Comps · higher is betterTest setup not documented as identical82.0%69.7%Vals AIAs of 11/05/2026

Finance Agent (v2)Adjustments · higher is betterTest setup not documented as identical54.4%49.8%Vals AIAs of 10/29/2026

ImmigrationAll-Pass · higher is betterTest setup not documented as identical26.3%16.4%Vals AIAs of 10/28/2026

IOIIOI 2024 · higher is betterTest setup not documented as identical100.0%69.3%Vals AIAs of 10/29/2026

Legal Research BenchAdministrative / Regulatory · All-pass · higher is betterTest setup not documented as identical68.2%37.9%Vals AIAs of 11/05/2026

LMArena Code Arena WebDevHTML development · higher is better1,6831,595LMArenaAs of 10/28/2026

LMArena Text, Style ControlBusiness, management and finance · higher is better1,4871,441LMArenaAs of 10/28/2026

LMArena Vision, Style ControlChinese · higher is better1,3511,292LMArenaAs of 10/19/2026

ProgramBenchAlmost Resolved · higher is betterTest setup not documented as identical53.5%8.0%Vals AIAs of 11/05/2026

SRE BenchCapability Score · higher is betterTest setup not documented as identical36.6%11.1%Vals AIAs of 11/05/2026

SWE-bench Multimodalbpmn-js · higher is betterTest setup not documented as identical79.2%56.6%Vals AIAs of 11/05/2026

Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identical26.7%6.7%Vals AIAs of 11/05/2026

Terminal-Bench 4.0Hardware · higher is betterTest setup not documented as identical60%0%Vals AIAs of 11/05/2026

Terminal-Bench-ScienceEarth Sciences · higher is betterTest setup not documented as identical25%0%Vals AIAs of 11/05/2026

Code MigrationCOBOL · higher is betterTest setup not documented as identical60.0%58.6%Vals AIAs of 10/29/2026

CyberBench v1.1PoC · higher is betterTest setup not documented as identical53.3%65.0%Vals AIAs of 11/05/2026

EMBDataroom · higher is betterTest setup not documented as identical86.7%75.5%Vals AIAs of 10/20/2026

EMB v1.1Dataroom · higher is betterTest setup not documented as identical88.5%82.1%Vals AIAs of 11/05/2026

Finance Agent (v2)All-Pass · higher is betterTest setup not documented as identical47.8%38.4%Vals AIAs of 10/29/2026

ImmigrationContent Checks · higher is betterTest setup not documented as identical73.2%60.8%Vals AIAs of 10/28/2026

IOIIOI 2025 · higher is betterTest setup not documented as identical87.2%39.0%Vals AIAs of 10/29/2026

Legal Research BenchAdministrative / Regulatory · Weighted partial credit (weighted pass) · higher is betterTest setup not documented as identical92.5%83.2%Vals AIAs of 11/05/2026

LMArena Code Arena WebDevImage to WebDev · higher is better1,7221,571LMArenaAs of 10/19/2026

LMArena Text, Style ControlChinese · higher is better1,5651,483LMArenaAs of 10/28/2026

LMArena Vision, Style ControlCreative writing with images · higher is better1,2901,232LMArenaAs of 10/19/2026

ProgramBenchFully Resolved · higher is betterTest setup not documented as identical7.0%0.5%Vals AIAs of 11/05/2026

SRE BenchFully Solved · higher is betterTest setup not documented as identical22.9%2.7%Vals AIAs of 11/05/2026

SWE-bench MultimodalCarbon · higher is betterTest setup not documented as identical44.4%19.5%Vals AIAs of 11/05/2026

Tax Agent BenchControversy & Precedence Analysis (weighted pass) · higher is betterTest setup not documented as identical70.6%54.4%Vals AIAs of 11/05/2026

Terminal-Bench 4.0Media · higher is betterTest setup not documented as identical66.7%16.7%Vals AIAs of 11/05/2026

Terminal-Bench-ScienceEngineering Sciences · higher is betterTest setup not documented as identical44.4%11.1%Vals AIAs of 11/05/2026

Code MigrationCode Quality · higher is betterTest setup not documented as identical4.513 / 53.752 / 5Vals AIAs of 10/29/2026

EMBDCF · higher is betterTest setup not documented as identical69.9%62.8%Vals AIAs of 10/20/2026

EMB v1.1DCF · higher is betterTest setup not documented as identical71.5%64.8%Vals AIAs of 11/05/2026

Finance Agent (v2)Comparables · higher is betterTest setup not documented as identical46.0%39.8%Vals AIAs of 10/29/2026

ImmigrationIntake Checks · higher is betterTest setup not documented as identical58.9%38.9%Vals AIAs of 10/28/2026

IOIIOI 2026 · higher is betterTest setup not documented as identical85.2%58.3%Vals AIAs of 10/29/2026

Legal Research BenchBusiness & Commercial · All-pass · higher is betterTest setup not documented as identical62.8%23.3%Vals AIAs of 11/05/2026

More comparisons

Compare Claude Fable 5.1 and GPT-6 Luna with the models people compare them with most often.

Claude Fable 5.1vs.GPT-6 Luna

Choose Claude Fable 5.1 for

Choose GPT-6 Luna for

Where is the difference?

Strengths at a glance

Claude Fable 5.1 vs. GPT-6 Luna at the same effort

Which model for which task?

See for yourself: same task, one attempt

Pelican on a bicycle

SVG short test

Claude Fable 5.1

GPT-6 Luna

Claude Fable 5.1 and GPT-6 Luna in the overall index

Overall index (Gradually Meta-Score v4)

Popularity compared

Over time

All data side by side

Is there a better choice?

Shared benchmarks

More comparisons

Compare another matchup

Predecessor and successor

The most popular comparisons