Enter opens the highlighted result. Esc closes.

GPT-6 Luna vs MiniMax M3

GPT-6 Luna leads MiniMax M3 on coding, 57.3 to 39.2 on the Vibe Coding Index, and GPT-6 Luna costs 2.4x less per output token ($0.50 vs $1.20 per million). Updated October 22, 2026; 86 benchmarks have a result for both.

Replace GPT-6 Luna Replace MiniMax M3
GPT-6 LunaOpenAI
Coding
57.3
Overall
59.7
Output $/M
$0.50
36
MiniMax M3MiniMax
Coding
39.2
Overall
51.7
Output $/M
$1.20
50
vs boards won of 86 shared

GPT-6 Luna or MiniMax M3: which to pick

Pick GPT-6 Luna for coding: it scores 57.3 on the Vibe Coding Index against 39.2 for MiniMax M3, though on 5 benchmarks against 6.

Pick MiniMax M3 for work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.

Model AGPT-6 LunaOpenAI57.3/1005 independent benchmarksNo cost per solved taskModel BMiniMax M3MiniMax39.2/1006 independent benchmarks$0.56 per solved task
Shared results
86
GPT-6 Luna only
18
MiniMax M3 only
31
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
GPT-6 Luna 57.3 from 5 benchmarks, MiniMax M3 39.2 from 6 benchmarks.
Widest category
Math, 20.2 points apart on average over 4 shared benchmarks.
Widest single gap
LiveBench browser: GPT-6 Luna 72.0% against MiniMax M3 8.0%, 64.0 points apart on a 0 to 100 scale.
Output price
GPT-6 Luna $0.50 against MiniMax M3 $1.20 per million output tokens, 2.4x apart.
Context window
GPT-6 Luna takes 1.05M tokens, MiniMax M3 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
CategoryGPT-6 LunaBarsMiniMax M3Ties
Coding142
Intelligence20
Agentic work65
Reasoning28
Math22
Knowledge05
Web design72
General326
All shared boards3650
CodingLike-for-likeSix of these boards feed the Vibe Coding Index142
Coding benchmarks for GPT-6 Luna and MiniMax M3
BenchmarkGPT-6 LunaMiniMax M3Leader
LiveBench coding84.5%70.9%GPT-6 Luna
LMArena WebDev15781482GPT-6 Luna
AA Coding IndexNot measured58.6Only MiniMax M3 measured
LiveCodeBench (Vals AI)Not measured82.2%Only MiniMax M3 measured
SWE-bench Verified (Vals AI)Not measured75.0%Only MiniMax M3 measured
Terminal-Bench 4 (Vals AI)13.6%1.0%GPT-6 Luna
Vibe Code Bench (Vals AI)81.7%47.6%GPT-6 Luna
Code migration (Vals AI)42.5%19.9%GPT-6 Luna
ProgramBench (Vals AI)0.5%Not measuredOnly GPT-6 Luna measured
IOI (Vals AI)55.6%Not measuredOnly GPT-6 Luna measured
Terminal-Bench 2.1 (Vals AI)73.0%53.6%GPT-6 Luna
SWE-bench Multimodal (Vals AI)37.5%33.3%GPT-6 Luna
Vibe Code Bench 1-100 (Vals AI)Not measured9.2%Only MiniMax M3 measured
SkillsBench (Vals AI)Not measured51.5%Only MiniMax M3 measured
CyberBench (Vals AI)76.3%65.0%GPT-6 Luna
SciCode54.6%47.1%GPT-6 Luna
Terminal-Bench Hard (Artificial Analysis run)Not measured42.4%Only MiniMax M3 measured
FrontierCode42.4%14.7%GPT-6 Luna
ALE-Bench1576.9640.0GPT-6 Luna
LMArena Text: coding14371470MiniMax M3
LMArena Text: software and IT14231466MiniMax M3
LMArena WebDev: React15731478GPT-6 Luna
LMArena WebDev: HTML15951455GPT-6 Luna
LMArena WebDev: from an image15711470GPT-6 Luna
Neither model has a result on the other 19 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GPT-6 Luna and MiniMax M3
BenchmarkGPT-6 LunaMiniMax M3Leader
AA Intelligence Index38.129.2GPT-6 Luna
Epoch Capabilities Index156.8146.9GPT-6 Luna
Agentic workLike-for-likePublic boards, shown as published, kept out of the index65
Agentic work benchmarks for GPT-6 Luna and MiniMax M3
BenchmarkGPT-6 LunaMiniMax M3Leader
AA Agentic IndexNot measured29.5Only MiniMax M3 measured
Design Arena: agents building web apps11911200MiniMax M3
Design Arena: agents building full-stack apps11581197MiniMax M3
Design Arena: agents building mobile apps11311169MiniMax M3
Design Arena: agents building Android appsNot measured1158Only MiniMax M3 measured
Design Arena: agents building gamesNot measured1159Only MiniMax M3 measured
Design Arena: HTML slidesNot measured1120Only MiniMax M3 measured
Design Arena: PowerPoint slidesNot measured1178Only MiniMax M3 measured
Design Arena: spreadsheetsNot measured1042Only MiniMax M3 measured
LiveBench research43.5%68.0%MiniMax M3
LiveBench browser72.0%8.0%GPT-6 Luna
LiveBench long agentic48.1%12.4%GPT-6 Luna
SREBench (Vals AI)2.7%Not measuredOnly GPT-6 Luna measured
Finance Agent (Vals AI)49.9%48.3%GPT-6 Luna
Tax Agent Bench (Vals AI)19.9%20.6%MiniMax M3
Legal Research Bench (Vals AI)30.3%29.8%GPT-6 Luna
Harvey's Legal Agent Benchmark (Vals AI)4.2%Not measuredOnly GPT-6 Luna measured
Excel Modeling Benchmark (Vals AI)68.5%47.8%GPT-6 Luna
BioMysteryBench (Vals AI)61.5%Not measuredOnly GPT-6 Luna measured
Terminal-Bench-Science (Vals AI)4.3%Not measuredOnly GPT-6 Luna measured
Vals Science Index28.4%Not measuredOnly GPT-6 Luna measured
τ²-Bench TelecomNot measured88.9%Only MiniMax M3 measured
APEX-Agents44.3%37.7%GPT-6 Luna
OSWorld 2.0Not measured4.6%Only MiniMax M3 measured
SpireClimb0.0%Not measuredOnly GPT-6 Luna measured
Vending-Bench 2Not measured$2,158Only MiniMax M3 measured
Neither model has a result on the other 16 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index28
Reasoning benchmarks for GPT-6 Luna and MiniMax M3
BenchmarkGPT-6 LunaMiniMax M3Leader
GPQA DiamondNot measured92.7%Only MiniMax M3 measured
LiveBench reasoning81.8%74.5%GPT-6 Luna
MysteryMechanism (Vals AI)19.4%Not measuredOnly GPT-6 Luna measured
MMMU Pro (Vals AI)Not measured81.2%Only MiniMax M3 measured
GPQA Diamond (Artificial Analysis run)Not measured92.9%Only MiniMax M3 measured
Humanity's Last Exam (Artificial Analysis run)38.5%39.0%MiniMax M3
GPQA Diamond (Epoch AI run)90.5%90.9%MiniMax M3
ARC-AGI86.7%Not measuredOnly GPT-6 Luna measured
ARC-AGI-259.3%Not measuredOnly GPT-6 Luna measured
SimpleBenchNot measured45.8%Only MiniMax M3 measured
Chess puzzles36.0%13.0%GPT-6 Luna
Mystery game puzzles7.0%8.0%MiniMax M3
LMArena Text: hard prompts14101447MiniMax M3
LMArena Text: expert14421461MiniMax M3
LMArena Text: hard prompts in English14101455MiniMax M3
LMArena Vision: diagrams12451266MiniMax M3
LMArena Vision: homework12611268MiniMax M3
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index22
Math benchmarks for GPT-6 Luna and MiniMax M3
BenchmarkGPT-6 LunaMiniMax M3Leader
OTIS Mock AIME98.9%71.1%GPT-6 Luna
FrontierMath, tiers 1 to 378.9%Not measuredOnly GPT-6 Luna measured
FrontierMath, tier 456.1%Not measuredOnly GPT-6 Luna measured
ProofBench64.0%18.0%GPT-6 Luna
LMArena Text: math14091429MiniMax M3
LMArena Text: mathematical work14271448MiniMax M3
Neither model has a result on the other 8 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index05
Knowledge benchmarks for GPT-6 Luna and MiniMax M3
BenchmarkGPT-6 LunaMiniMax M3Leader
MMLU ProNot measured84.2%Only MiniMax M3 measured
LegalBench (Vals AI)Not measured85.4%Only MiniMax M3 measured
CorpFin (Vals AI)Not measured68.1%Only MiniMax M3 measured
TaxEval (Vals AI)Not measured72.7%Only MiniMax M3 measured
MortgageTax (Vals AI)Not measured68.4%Only MiniMax M3 measured
MedCode (Vals AI)44.7%46.3%MiniMax M3
SimpleQA Verified41.4%Not measuredOnly GPT-6 Luna measured
LMArena Text: science13861452MiniMax M3
LMArena Text: medicine and healthcare13521441MiniMax M3
LMArena Text: legal and government14001437MiniMax M3
LMArena Text: business and finance13881434MiniMax M3
FACTS Benchmark Suite63.3%Not measuredOnly GPT-6 Luna measured
PRBench Legal42.9%Not measuredOnly GPT-6 Luna measured
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index72
Web design benchmarks for GPT-6 Luna and MiniMax M3
BenchmarkGPT-6 LunaMiniMax M3Leader
Design Arena: websites12711257GPT-6 Luna
Design Arena: UI components12951243GPT-6 Luna
Design Arena: game dev12581210GPT-6 Luna
Design Arena: data viz12171236MiniMax M3
Design Arena: 3D12181208GPT-6 Luna
Design Arena: all code categories12701246GPT-6 Luna
Design Arena: SVG12531160GPT-6 Luna
Design Arena: ASCII art11531161MiniMax M3
LiveBench design82.5%66.2%GPT-6 Luna
GeneralLike-for-likePublic boards, shown as published, kept out of the index326
General benchmarks for GPT-6 Luna and MiniMax M3
BenchmarkGPT-6 LunaMiniMax M3Leader
Vals Index52.3%Not measuredOnly GPT-6 Luna measured
LiveBench data analysis73.4%76.2%MiniMax M3
Public Benefits Bench (Vals AI)57.6%64.1%MiniMax M3
SAGE (Vals AI)48.1%50.6%MiniMax M3
MedScribe (Vals AI)83.7%87.3%MiniMax M3
Vals Multimodal IndexNot measured60.0%Only MiniMax M3 measured
IFBenchNot measured82.9%Only MiniMax M3 measured
Long context reasoning (AA-LCR)83.3%83.0%GPT-6 Luna
DTBench90.1%78.9%GPT-6 Luna
LMCA44.5%33.7%GPT-6 Luna
Surface Evolver BenchNot measured55.0%Only MiniMax M3 measured
Furniture assembly44.2%Not measuredOnly GPT-6 Luna measured
LMArena Text13891433MiniMax M3
LMArena Text: instruction following14081433MiniMax M3
LMArena Text: creative writing13631404MiniMax M3
LMArena Vision12161251MiniMax M3
LMArena Text: English13931443MiniMax M3
LMArena Text: non-English13811420MiniMax M3
LMArena Text: Chinese14271466MiniMax M3
LMArena Text: German13761428MiniMax M3
LMArena Text: Japanese13691380MiniMax M3
LMArena Text: Korean13591373MiniMax M3
LMArena Text: French14081444MiniMax M3
LMArena Text: Spanish13911433MiniMax M3
LMArena Text: Russian13921426MiniMax M3
LMArena Text: Polish13831423MiniMax M3
LMArena Text: multi-turn13921443MiniMax M3
LMArena Text: longer queries14081446MiniMax M3
LMArena Text: writing and language13841419MiniMax M3
LMArena Text: entertainment and media13641403MiniMax M3
LMArena Vision: English12041263MiniMax M3
LMArena Vision: Chinese12661311MiniMax M3
LMArena Vision: reading text12251259MiniMax M3
LMArena Vision: humorNot measured1235Only MiniMax M3 measured
LMArena Vision: recognizing thingsNot measured1197Only MiniMax M3 measured
LMArena Vision: creative writing12051234MiniMax M3
LMArena DocumentNot measured1435Only MiniMax M3 measured
EQ-Bench 4Not measured1150Only MiniMax M3 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 GPT-6 Luna and MiniMax M3
BenchmarkGPT-6 LunaMiniMax M3Leader
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

GPT-6 Luna$0.0003Fits in one request
MiniMax M3$0.0009Fits in one request

GPT-6 Luna costs less

Repository review

50K input + 3K output tokens

GPT-6 Luna$0.0065Fits in one request
MiniMax M3$0.019Fits in one request

GPT-6 Luna costs less

Agent loop

200K input + 10K output tokens

GPT-6 Luna$0.025Fits in one request
MiniMax M3$0.072Fits 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 GPT-6 Luna and MiniMax M3
SpecificationOpenAI GPT-6 LunaMiniMax M3
MakerOpenAIMiniMax
WeightsNo public weights listedOpen weights
ReleasedSeptember 22, 2026May 31, 2026
Context window1.05M1.05M
Input $/Mtok$0.10$0.30
Output $/Mtok$0.50$1.20
Coding index57.339.2
Independent measurements behind it56
Cost per solved taskNot computable$0.56
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-6 Luna better than MiniMax M3 for coding?

Pick GPT-6 Luna for coding: it scores 57.3 on the Vibe Coding Index against 39.2 for MiniMax M3, though on 5 benchmarks against 6. Pick MiniMax M3 for work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.

Which is cheaper, GPT-6 Luna or MiniMax M3?

GPT-6 Luna costs $0.10 per million input tokens and $0.50 per million output tokens; MiniMax M3 costs $0.30 and $1.20. Cost per solved task is known for MiniMax M3 only.

Which has the bigger context window, GPT-6 Luna or MiniMax M3?

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

How many benchmarks is the GPT-6 Luna vs MiniMax M3 comparison based on?

86 benchmarks have a result for both models as of October 22, 2026. GPT-6 Luna's coding index rests on 5 independent benchmarks and MiniMax M3's on 6. 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/gpt-6-luna-vs-minimax-minimax-m3" title="GPT-6 Luna vs MiniMax M3, 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/gpt-6-luna-vs-minimax-minimax-m3">LLMBenchmark.ai, GPT-6 Luna vs MiniMax M3</a></p>