OpenAIMistral AILLM matchup

GPT-6 Lunavs.Mistral Large 3

Which one is better?

GPT-6 Luna performs better than Mistral Large 3 and is cheaper: Mistral Large 3 costs 5 times (input) and 3 times (output) as much.

GPT-6 Luna ahead

IntelligenceOverall index, 100 points = average

96.3

GPT-6 Luna

Rank 35

38.8

Mistral Large 3

Rank 92

GPT-6 Luna faster

SpeedTokens per second

101

GPT-6 Luna

Mistral Large 3

GPT-6 Luna cheaper

Price$ per 1M tokens

$0.20

GPT-6 Luna

$0.75

Mistral Large 3

GPT-6 Luna more popular

Popularity0 to 100

GPT-6 Luna

Rank 30 of 785

Mistral Large 3

Rank 476 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

MathematicsCodingAgentsReasoningHealthFinanceMultimodalGeneralLegalKnowledge

Choose Mistral Large 3 for

No clear advantage

Where is the difference?

Strengths at a glance

GPT-6 LunaMistral Large 3Median of all ranked models

CodingGPT-6 Luna ahead

GPT-6 Luna97.5Rank 35

Mistral Large 338.3Rank 104

Median of ranked models84.1

95 % range: GPT-6 Luna 94.5 to 100.5, Mistral Large 3 29.0 to 47.6.

AreaGPT-6 LunaMistral Large 3

The same values and verdicts as the bars below. In the close-up the net starts at 25 points, just below the weaker model's lowest value; the reference group average is 100.

GPT-6 Luna is ahead in 10 of 10 areas, Mistral Large 3 in none.

GPT-6 Luna ahead: 10

Areas in the overall index

MathematicsGPT-6 Luna +73105.5 to 32.9

CodingGPT-6 Luna +5997.5 to 38.3

AgentsGPT-6 Luna +5899.5 to 41.7

ReasoningGPT-6 Luna +5797.8 to 41.3

MultimodalGPT-6 Luna +5292.0 to 40.0

GeneralGPT-6 Luna +5294.4 to 42.8

KnowledgeGPT-6 Luna +4689.2 to 43.7

Specialist fields

HealthGPT-6 Luna +5695.2 to 39.3

FinanceGPT-6 Luna +5398.3 to 45.7

LegalGPT-6 Luna +4690.7 to 44.5

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 38.3

Maths and data analysisGPT-6 LunaMathematics 105.5 to 32.9, Reasoning 97.8 to 41.3

Facts and researchGPT-6 LunaKnowledge 89.2 to 43.7, Search without a score for Mistral Large 3

Agents and workflowsGPT-6 LunaAgents 99.5 to 41.7

Fast chat repliesGPT-6 Luna101 to 78 tokens per second

Security analysisopenCybersecurity without a score for Mistral Large 3

Many requests on a small budgetGPT-6 Luna$0.20 to $0.75 per 1M tokens

Finance, legal and medical textsGPT-6 LunaFinance 98.3 to 45.7, Legal 90.7 to 44.5, Health 95.2 to 39.3

Images, screenshots and PDFsGPT-6 LunaMultimodal 92.0 to 40.0

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

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.

Mistral Large 3

Oct 1, 2026 · 14 s · $0.0022

Test details

Run date: Oct 1, 2026
API provider: openrouter
Requested API model: mistralai/mistral-large-2512
Reasoning setting: not specified
Token limit including reasoning: 8,192 tokens
Output tokens: 1,451 tokens
Cost of the attempt: $0.0022
Response time: 14.2 s
API model reported in response: mistralai/mistral-large-2512
Pinned endpoint: Mistral | mistralai/mistral-large-2512
Temperature: Provider default
Test protocol: community-visual-tests-v1
Technical checks: Passed, not a quality rating
Reasoning (model default): no reasoning mode Source

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

Earlier attempts (1)

Sep 7, 2026API request failedReasoning setting: not specified

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

Mistral Large 3

API request failed. The model was not evaluated.

GPT-6 Luna and Mistral Large 3 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

Mistral Large 3none38.8

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

Mistral Large 3

Popularity compared

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

GPT-6 Luna is more popular than Mistral Large 3: 60 to 32 out of 100.

Over time

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

GPT-6 LunaMistral Large 3

All data side by side

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

Metric	GPT-6 Luna	Mistral Large 3
Intelligence
Overall indexpoints, 100 = reference group average, higher is better	96.3	38.8
Rank	Rank 35 of 92	Rank 92 of 92
Price per 1M tokens
Inputwhat you send	$0.10above 272,000 tokens: $0.20	$0.50
Outputwhat the model writes	$0.50above 272,000 tokens: $0.75	$1.50
Cost per task (own tests)average of 1 original-protocol task both models passed (SVG short test not included)	$0.002	$0.002
Speed
Tokens per second	101	78
Popularity
Popularitysearch, usage and mentions, 0 to 100	60Rank 30 of 785	32Rank 476 of 785
Technical
Context windowhow much text the model reads at once	1.05 M tokens≈ 1,580 A4 pages	262,144 tokens≈ 390 A4 pages
Knowledge cutoff	May 18, 2026	n/a
Released	Sep 22, 2026	Dec 2, 2025
Availability	Active	Active
Open weights	no	yes

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: Mistral Large 3

LMArena Code Arena WebDevOverall · higher is betterTest setup not documented as identical1,5791,233LMArenaAs of 10/28/2026

LMArena Text, Style ControlOverall · higher is betterTest setup not documented as identical1,4411,414LMArenaAs of 10/28/2026

LMArena Vision, Style ControlOverall · higher is betterTest setup not documented as identical1,2401,199LMArenaAs of 10/19/2026

LMArena Code Arena WebDevHTML development · higher is betterTest setup not documented as identical1,5951,241LMArenaAs of 10/28/2026

LMArena Text, Style ControlBusiness, management and finance · higher is betterTest setup not documented as identical1,4411,410LMArenaAs of 10/28/2026

LMArena Vision, Style ControlChinese · higher is betterTest setup not documented as identical1,2921,218LMArenaAs of 10/19/2026

LMArena Code Arena WebDevImage to WebDev · higher is betterTest setup not documented as identical1,5711,361LMArenaAs of 10/19/2026

LMArena Text, Style ControlChinese · higher is betterTest setup not documented as identical1,4831,432LMArenaAs of 10/28/2026

LMArena Vision, Style ControlCreative writing with images · higher is betterTest setup not documented as identical1,2321,197LMArenaAs of 10/19/2026

LMArena Code Arena WebDevWeb development · higher is betterTest setup not documented as identical1,5791,233LMArenaAs of 10/28/2026

Show 30 more benchmarks

LMArena Text, Style ControlCoding · higher is betterTest setup not documented as identical1,5061,471LMArenaAs of 10/28/2026

LMArena Vision, Style ControlDiagram understanding · higher is betterTest setup not documented as identical1,2751,233LMArenaAs of 10/19/2026

LMArena Text, Style ControlCreative writing · higher is betterTest setup not documented as identical1,4101,375LMArenaAs of 10/28/2026

LMArena Vision, Style ControlEnglish · higher is betterTest setup not documented as identical1,2281,209LMArenaAs of 10/19/2026

LMArena Text, Style ControlEnglish · higher is betterTest setup not documented as identical1,4491,427LMArenaAs of 10/28/2026

LMArena Vision, Style ControlHomework · higher is betterTest setup not documented as identical1,2811,206LMArenaAs of 10/19/2026

LMArena Text, Style ControlEntertainment, sports and media · higher is betterTest setup not documented as identical1,4131,373LMArenaAs of 10/28/2026

LMArena Vision, Style ControlOptical character recognition · higher is betterTest setup not documented as identical1,2511,214LMArenaAs of 10/19/2026

LMArena Text, Style ControlExcluding ties · higher is betterTest setup not documented as identical1,4411,402LMArenaAs of 10/28/2026

LMArena Text, Style ControlExpert prompts · higher is betterTest setup not documented as identical1,4891,428LMArenaAs of 10/28/2026

LMArena Text, Style ControlFrench prompts · higher is betterTest setup not documented as identical1,4671,432LMArenaAs of 10/28/2026

LMArena Text, Style ControlGerman prompts · higher is betterTest setup not documented as identical1,4351,411LMArenaAs of 10/28/2026

LMArena Text, Style ControlHard prompts · higher is betterTest setup not documented as identical1,4641,433LMArenaAs of 10/28/2026

LMArena Text, Style ControlHard prompts, English · higher is betterTest setup not documented as identical1,4701,440LMArenaAs of 10/28/2026

LMArena Text, Style ControlInstruction following · higher is betterTest setup not documented as identical1,4381,403LMArenaAs of 10/28/2026

LMArena Text, Style ControlJapanese prompts · higher is betterTest setup not documented as identical1,4211,379LMArenaAs of 10/28/2026

LMArena Text, Style ControlKorean prompts · higher is betterTest setup not documented as identical1,4081,358LMArenaAs of 10/28/2026

LMArena Text, Style ControlLegal and government · higher is betterTest setup not documented as identical1,4481,422LMArenaAs of 10/28/2026

LMArena Text, Style ControlLife, physical and social science · higher is betterTest setup not documented as identical1,4531,429LMArenaAs of 10/28/2026

LMArena Text, Style ControlLonger queries · higher is betterTest setup not documented as identical1,4511,418LMArenaAs of 10/28/2026

LMArena Text, Style ControlMath · higher is betterTest setup not documented as identical1,4471,401LMArenaAs of 10/28/2026

LMArena Text, Style ControlMathematical professions · higher is betterTest setup not documented as identical1,4661,414LMArenaAs of 10/28/2026

LMArena Text, Style ControlMedicine and healthcare · higher is betterTest setup not documented as identical1,4331,431LMArenaAs of 10/28/2026

LMArena Text, Style ControlMulti-turn · higher is betterTest setup not documented as identical1,4411,420LMArenaAs of 10/28/2026

LMArena Text, Style ControlNon-English · higher is betterTest setup not documented as identical1,4291,398LMArenaAs of 10/28/2026

LMArena Text, Style ControlPolish prompts · higher is betterTest setup not documented as identical1,4461,415LMArenaAs of 10/28/2026

LMArena Text, Style ControlRussian prompts · higher is betterTest setup not documented as identical1,4381,407LMArenaAs of 10/28/2026

LMArena Text, Style ControlSoftware and IT services · higher is betterTest setup not documented as identical1,4911,456LMArenaAs of 10/28/2026

LMArena Text, Style ControlSpanish prompts · higher is betterTest setup not documented as identical1,4421,408LMArenaAs of 10/28/2026

LMArena Text, Style ControlWriting, literature and language · higher is betterTest setup not documented as identical1,4241,390LMArenaAs of 10/28/2026

More comparisons

Compare GPT-6 Luna and Mistral Large 3 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 52 comparisons