OpenAILLM matchup

GPT-6 Lunavs.GPT-5.4 mini

Is the higher price worth it?

GPT-6 Luna performs better than GPT-5.4 mini and is cheaper: GPT-5.4 mini costs 7.5 times (input) and 9 times (output) as much.

GPT-6 Luna ahead

IntelligenceOverall index, 100 points = average

96.3

GPT-6 Luna

Rank 35

75.6

GPT-5.4 mini

Rank 56

GPT-5.4 mini faster

SpeedTokens per second

101

GPT-6 Luna

191

GPT-5.4 mini

GPT-6 Luna cheaper

Price$ per 1M tokens

$0.20

GPT-6 Luna

$1.69

GPT-5.4 mini

about as popular

Popularity0 to 100

GPT-6 Luna

Rank 30 of 785

GPT-5.4 mini

Rank 38 of 785

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

Choose GPT-6 Luna for

ReasoningFinanceCodingAgentsLegalMultimodalKnowledgeGeneral

Choose GPT-5.4 mini for

No clear advantage

Where is the difference?

Strengths at a glance

GPT-6 LunaGPT-5.4 miniMedian of all ranked models

CodingGPT-6 Luna ahead

GPT-6 Luna97.5Rank 35

GPT-5.4 mini75.8Rank 65

Median of ranked models84.1

95 % range: GPT-6 Luna 94.5 to 100.5, GPT-5.4 mini 71.9 to 79.8.

AreaGPT-6 LunaGPT-5.4 mini

The same values and verdicts as the bars below. In the close-up the net starts at 65 points, just below the weaker model's lowest value; the reference group average is 100. Not in the net because a model has no own value there or the data are too thin: Mathematics, Health.

GPT-6 Luna is ahead in 8 of 10 areas, GPT-5.4 mini in none.

GPT-6 Luna ahead: 8too little data: 2

Areas in the overall index

ReasoningGPT-6 Luna +2497.8 to 74.3

CodingGPT-6 Luna +2297.5 to 75.8

AgentsGPT-6 Luna +2099.5 to 79.0

MultimodalGPT-6 Luna +1592.0 to 76.5

KnowledgeGPT-6 Luna +1489.2 to 74.9

GeneralGPT-6 Luna +1494.4 to 80.4

Mathematicsonly GPT-6 Luna has a score

Specialist fields

FinanceGPT-6 Luna +2398.3 to 75.7

LegalGPT-6 Luna +1890.7 to 73.1

Healthonly 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.

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

Cybersecurityonly GPT-6 Luna has a score

Searchonly GPT-6 Luna has a score

Productivityonly 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.

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 codeGPT-6 LunaCoding 97.5 to 75.8

Maths and data analysisGPT-6 LunaMathematics without a score for GPT-5.4 mini, Reasoning 97.8 to 74.3

Facts and researchGPT-6 LunaKnowledge 89.2 to 74.9, Search without a score for GPT-5.4 mini

Agents and workflowsGPT-6 LunaAgents 99.5 to 79.0

Fast chat repliesGPT-5.4 mini101 to 191 tokens per second

Security analysisopenCybersecurity without a score for GPT-5.4 mini

Many requests on a small budgetGPT-6 Luna$0.20 to $1.69 per 1M tokens

Finance, legal and medical textsGPT-6 LunaFinance 98.3 to 75.7, Legal 90.7 to 73.1, Health without a score for GPT-5.4 mini

Images, screenshots and PDFsGPT-6 LunaMultimodal 92.0 to 76.5

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

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.

GPT-5.4 mini

Oct 2, 2026 · 14 s · $0.01

Test details

Run date: Oct 2, 2026
API provider: openrouter
Requested API model: openai/gpt-5.4-mini
Reasoning setting: high
Token limit including reasoning: 8,192 tokens
Output tokens: 3,142 tokens
Cost of the attempt: $0.0142
Response time: 13.5 s
API model reported in response: openai/gpt-5.4-mini
Pinned endpoint: OpenAI | openai/gpt-5.4-mini-20260317
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.

Earlier attempts (2)

Oct 1, 2026API request failedReasoning setting: high
Sep 7, 2026API request failedReasoning setting: high

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.

GPT-6 Luna

Unavailable in this round

GPT-5.4 mini

Unavailable in this round

GPT-6 Luna and GPT-5.4 mini 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

5 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 Lunamax96.3

GPT-5.4 minixhigh75.6

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 Luna

GPT-5.4 mini

Popularity compared

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

Both are about as popular: GPT-6 Luna 60, GPT-5.4 mini 59 out of 100.

Over time

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

GPT-6 LunaGPT-5.4 mini

All data side by side

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

Metric	GPT-6 Luna	GPT-5.4 mini
Intelligence
Overall indexpoints, 100 = reference group average, higher is better	96.3	75.6
Rank	Rank 35 of 92	Rank 56 of 92
Price per 1M tokens
Inputwhat you send	$0.10above 272,000 tokens: $0.20	$0.75
Outputwhat the model writes	$0.50above 272,000 tokens: $0.75	$4.50
Cost per task (own tests)average of 1 original-protocol task both models passed (SVG short test not included)	$0.002	$0.014
Speed
Tokens per second	101	191
Popularity
Popularitysearch, usage and mentions, 0 to 100	60Rank 30 of 785	59Rank 38 of 785
Technical
Context windowhow much text the model reads at once	1.05 M tokens≈ 1,580 A4 pages	400,000 tokens≈ 600 A4 pages
Knowledge cutoff	May 18, 2026	Aug 31, 2025
Released	Sep 22, 2026	Mar 17, 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

GPT-6 Luna 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

GPT-6 Luna 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: GPT-6 LunaB: GPT-5.4 mini

Code MigrationOverall · higher is betterTest setup not documented as identical42.6%12.9%Vals AIAs of 10/29/2026

EMBOverall · higher is betterTest setup not documented as identical68.5%45.4%Vals AIAs of 10/20/2026

Finance Agent (v2)Overall · higher is betterTest setup not documented as identical49.9%45.4%Vals AIAs of 10/29/2026

GDPval-AAOverall · higher is better1,372.5 elo1,021.8 eloArtificial AnalysisAs of 11/07/2026

Legal Research BenchOverall · All-pass · higher is betterTest setup not documented as identical30.3%12.5%Vals AIAs of 11/05/2026

LMArena Code Arena WebDevOverall · higher is betterTest setup not documented as identical1,5791,397LMArenaAs of 10/28/2026

LMArena Text, Style ControlOverall · higher is betterTest setup not documented as identical1,4411,447LMArenaAs of 10/28/2026

LMArena Vision, Style ControlOverall · higher is betterTest setup not documented as identical1,2401,250LMArenaAs of 10/19/2026

MMMU-ProOverall · higher is better79.7%73.3%Artificial AnalysisAs of 11/07/2026

ProgramBenchOverall · higher is betterTest setup not documented as identical0.5%0.0%Vals AIAs of 11/05/2026

Show 54 more benchmarks

Tax Agent BenchOverall · higher is betterTest setup not documented as identical19.9%8.8%Vals AIAs of 11/05/2026

Terminal-Bench 4.0Overall · higher is betterTest setup not documented as identical13.6%2.5%Vals AIAs of 11/05/2026

Vibe Code Bench v1.1Overall · higher is betterTest setup not documented as identical81.6%48.0%Vals AIAs of 11/05/2026

Code MigrationCLI · higher is betterTest setup not documented as identical37.2%8.2%Vals AIAs of 10/29/2026

EMBComps · higher is betterTest setup not documented as identical70.5%40.5%Vals AIAs of 10/20/2026

Finance Agent (v2)Adjustments · higher is betterTest setup not documented as identical49.8%45.4%Vals AIAs of 10/29/2026

Legal Research BenchAdministrative / Regulatory · All-pass · higher is betterTest setup not documented as identical37.9%15.2%Vals AIAs of 11/05/2026

LMArena Code Arena WebDevHTML development · higher is betterTest setup not documented as identical1,5951,419LMArenaAs of 10/28/2026

LMArena Text, Style ControlBusiness, management and finance · higher is betterTest setup not documented as identical1,4411,459LMArenaAs of 10/28/2026

LMArena Vision, Style ControlChinese · higher is betterTest setup not documented as identical1,2921,285LMArenaAs of 10/19/2026

ProgramBenchAlmost Resolved · higher is betterTest setup not documented as identical8%3%Vals AIAs of 11/05/2026

Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identical6.7%3.3%Vals AIAs of 11/05/2026

Terminal-Bench 4.0Hardware · higher is betterTest setup not documented as identical0%0%Vals AIAs of 11/05/2026

Code MigrationCOBOL · higher is betterTest setup not documented as identical58.6%27.1%Vals AIAs of 10/29/2026

EMBDataroom · higher is betterTest setup not documented as identical75.5%48.3%Vals AIAs of 10/20/2026

Finance Agent (v2)All-Pass · higher is betterTest setup not documented as identical38.4%32.4%Vals AIAs of 10/29/2026

Legal Research BenchAdministrative / Regulatory · Weighted partial credit (weighted pass) · higher is betterTest setup not documented as identical83.2%69.7%Vals AIAs of 11/05/2026

LMArena Code Arena WebDevReact development · higher is betterTest setup not documented as identical1,5751,386LMArenaAs of 10/28/2026

LMArena Text, Style ControlChinese · higher is betterTest setup not documented as identical1,4831,474LMArenaAs of 10/28/2026

LMArena Vision, Style ControlCreative writing with images · higher is betterTest setup not documented as identical1,2321,226LMArenaAs of 10/19/2026

ProgramBenchFully Resolved · higher is betterTest setup not documented as identical0.5%0.0%Vals AIAs of 11/05/2026

Tax Agent BenchControversy & Precedence Analysis (weighted pass) · higher is betterTest setup not documented as identical54.4%32.2%Vals AIAs of 11/05/2026

Terminal-Bench 4.0Media · higher is betterTest setup not documented as identical16.7%0.0%Vals AIAs of 11/05/2026

Code MigrationCode Quality · higher is betterTest setup not documented as identical3.752 / 53.053 / 5Vals AIAs of 10/29/2026

EMBDCF · higher is betterTest setup not documented as identical62.8%40.6%Vals AIAs of 10/20/2026

Finance Agent (v2)Comparables · higher is betterTest setup not documented as identical39.8%40.3%Vals AIAs of 10/29/2026

Legal Research BenchBusiness & Commercial · All-pass · higher is betterTest setup not documented as identical23.3%11.6%Vals AIAs of 11/05/2026

LMArena Code Arena WebDevWeb development · higher is betterTest setup not documented as identical1,5791,397LMArenaAs of 10/28/2026

LMArena Text, Style ControlCoding · higher is betterTest setup not documented as identical1,5061,495LMArenaAs of 10/28/2026

LMArena Vision, Style ControlDiagram understanding · higher is betterTest setup not documented as identical1,2751,283LMArenaAs of 10/19/2026

ProgramBenchRaw Pass Rate · higher is betterTest setup not documented as identical66.2%54.4%Vals AIAs of 11/05/2026

Tax Agent BenchCurrent & Temporal Analysis · higher is betterTest setup not documented as identical16.5%10.0%Vals AIAs of 11/05/2026

Terminal-Bench 4.0ML · higher is betterTest setup not documented as identical9.1%0.0%Vals AIAs of 11/05/2026

EMBLBO · higher is betterTest setup not documented as identical59.1%41.6%Vals AIAs of 10/20/2026

Finance Agent (v2)Disclosure Analysis · higher is betterTest setup not documented as identical57.6%48.3%Vals AIAs of 10/29/2026

Legal Research BenchBusiness & Commercial · Weighted partial credit (weighted pass) · higher is betterTest setup not documented as identical79.1%71.2%Vals AIAs of 11/05/2026

LMArena Text, Style ControlCreative writing · higher is betterTest setup not documented as identical1,4101,402LMArenaAs of 10/28/2026

LMArena Vision, Style ControlEnglish · higher is betterTest setup not documented as identical1,2281,248LMArenaAs of 10/19/2026

Tax Agent BenchCurrent & Temporal Analysis (weighted pass) · higher is betterTest setup not documented as identical55.3%38.6%Vals AIAs of 11/05/2026

Terminal-Bench 4.0Operations · higher is betterTest setup not documented as identical3.7%0.0%Vals AIAs of 11/05/2026

EMBM&A · higher is betterTest setup not documented as identical72.1%49.8%Vals AIAs of 10/20/2026

Finance Agent (v2)Earnings Analysis · higher is betterTest setup not documented as identical74.2%65.3%Vals AIAs of 10/29/2026

Legal Research BenchCivil Litigation · All-pass · higher is betterTest setup not documented as identical25.9%14.8%Vals AIAs of 11/05/2026

LMArena Text, Style ControlEnglish · higher is betterTest setup not documented as identical1,4491,450LMArenaAs of 10/28/2026

LMArena Vision, Style ControlHomework · higher is betterTest setup not documented as identical1,2811,291LMArenaAs of 10/19/2026

Tax Agent BenchFact-Pattern Analysis · higher is betterTest setup not documented as identical29.5%7.0%Vals AIAs of 11/05/2026

Terminal-Bench 4.0Science · higher is betterTest setup not documented as identical21.4%2.4%Vals AIAs of 11/05/2026

EMBMisc · higher is betterTest setup not documented as identical68.6%46.3%Vals AIAs of 10/20/2026

Finance Agent (v2)Financial Modeling · higher is betterTest setup not documented as identical22.5%19.6%Vals AIAs of 10/29/2026

Legal Research BenchCivil Litigation · Weighted partial credit (weighted pass) · higher is betterTest setup not documented as identical78.6%67.3%Vals AIAs of 11/05/2026

LMArena Text, Style ControlEntertainment, sports and media · higher is betterTest setup not documented as identical1,4131,409LMArenaAs of 10/28/2026

LMArena Vision, Style ControlOptical character recognition · higher is betterTest setup not documented as identical1,2511,262LMArenaAs of 10/19/2026

Tax Agent BenchFact-Pattern Analysis (weighted pass) · higher is betterTest setup not documented as identical60.2%36.5%Vals AIAs of 11/05/2026

Terminal-Bench 4.0Security · higher is betterTest setup not documented as identical26.7%0.0%Vals AIAs of 11/05/2026

More comparisons

Compare GPT-6 Luna and GPT-5.4 mini with the models people compare them with most often.

Compare another matchup

First modelSecond model

Predecessor and successor

PredecessorGPT-6 Luna vs. GPT-5.6 LunaPredecessor of GPT-6 Luna

The most popular comparisons

Show all 50 comparisons