LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Gemini 4 Argon vs GPT-6 Luna

Updated October 21, 2026. 83 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Gemini 4 Argon Replace GPT-6 Luna
Gemini 4 ArgonGoogle
Coding
80.5
Overall
52.6
Output $/M
$10.00
80
GPT-6 LunaOpenAI
Coding
71.4
Overall
38.1
Output $/M
$0.50
3
vs boards won of 83 shared

Decision reading

Pick Gemini 4 Argon for coding: it scores 80.5 on the Vibe Coding Index against 71.4 for GPT-6 Luna.

Pick GPT-6 Luna when output tokens cost 20.0x less, or when the context window is larger, 1.05M against 1.05M tokens.

Model AGemini 4 ArgonGoogle80.5/1002 independent benchmarksNo cost per solved taskModel BGPT-6 LunaOpenAI71.4/1002 independent benchmarksNo cost per solved task
Shared results
83
Gemini 4 Argon only
9
GPT-6 Luna only
19
Like-for-like categories
8 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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
Gemini 4 Argon 80.5 from 2 benchmarks, GPT-6 Luna 71.4 from 2 benchmarks.
Widest category
Knowledge, 26.2 points apart on average over 6 shared benchmarks.
Widest single gap
Mystery game puzzles: Gemini 4 Argon 64.0% against GPT-6 Luna 7.0%, 57.0 points apart on a 0 to 100 scale.
Output price
Gemini 4 Argon $10.00 against GPT-6 Luna $0.50 per million output tokens, 20.0x apart.
Context window
Gemini 4 Argon takes 1.05M 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
CategoryGemini 4 ArgonBarsGPT-6 LunaTies
Coding161
Intelligence20
Agentic work130
Reasoning110
Math60
Knowledge60
Web design61
General201
All shared boards803
CodingLike-for-likeFour of these boards feed the Vibe Coding Index161
Coding benchmarks for Gemini 4 Argon and GPT-6 Luna
BenchmarkGemini 4 ArgonGPT-6 LunaLeader
LiveBench coding89.7%84.5%Gemini 4 Argon
LMArena WebDev16781578Gemini 4 Argon
Terminal-Bench 4 (Vals AI)57.6%13.6%Gemini 4 Argon
Vibe Code Bench (Vals AI)91.9%81.7%Gemini 4 Argon
Code migration (Vals AI)68.2%42.5%Gemini 4 Argon
ProgramBench (Vals AI)2.5%0.5%Gemini 4 Argon
IOI (Vals AI)100.0%55.6%Gemini 4 Argon
Terminal-Bench 2.1 (Vals AI)57.7%73.0%GPT-6 Luna
SWE-bench Multimodal (Vals AI)56.0%37.5%Gemini 4 Argon
Vibe Code Bench 1-100 (Vals AI)21.2%Not measuredOnly Gemini 4 Argon measured
CyberBench (Vals AI)77.9%76.3%Gemini 4 Argon
SciCode61.8%54.6%Gemini 4 Argon
FrontierCode47.5%42.4%Gemini 4 Argon
FrontierSWE55.0%Not measuredOnly Gemini 4 Argon measured
ALE-Bench2100.11576.9Gemini 4 Argon
LMArena Text: coding15461437Gemini 4 Argon
LMArena Text: software and IT15561423Gemini 4 Argon
LMArena WebDev: React16921573Gemini 4 Argon
LMArena WebDev: HTML16431595Gemini 4 Argon
LMArena WebDev: from an imageNot measured1571Only GPT-6 Luna measured
Neither model has a result on the other 18 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Gemini 4 Argon and GPT-6 Luna
BenchmarkGemini 4 ArgonGPT-6 LunaLeader
AA Intelligence Index52.638.1Gemini 4 Argon
Epoch Capabilities Index166.4156.8Gemini 4 Argon
Agentic workLike-for-likePublic boards, shown as published, kept out of the index130
Agentic work benchmarks for Gemini 4 Argon and GPT-6 Luna
BenchmarkGemini 4 ArgonGPT-6 LunaLeader
Design Arena: agents building web appsNot measured1189Only GPT-6 Luna measured
Design Arena: agents building full-stack appsNot measured1158Only GPT-6 Luna measured
Design Arena: agents building mobile appsNot measured1133Only GPT-6 Luna measured
Design Arena: spreadsheets1151Not measuredOnly Gemini 4 Argon measured
LiveBench research83.1%43.5%Gemini 4 Argon
LiveBench browser92.0%72.0%Gemini 4 Argon
LiveBench long agentic69.9%48.1%Gemini 4 Argon
SREBench (Vals AI)44.3%2.7%Gemini 4 Argon
Finance Agent (Vals AI)65.4%49.9%Gemini 4 Argon
Tax Agent Bench (Vals AI)44.6%19.9%Gemini 4 Argon
Legal Research Bench (Vals AI)54.8%30.3%Gemini 4 Argon
Harvey's Legal Agent Benchmark (Vals AI)27.1%4.2%Gemini 4 Argon
Excel Modeling Benchmark (Vals AI)75.2%68.5%Gemini 4 Argon
BioMysteryBench (Vals AI)76.3%61.5%Gemini 4 Argon
Terminal-Bench-Science (Vals AI)44.3%4.3%Gemini 4 Argon
Vals Science Index55.4%28.4%Gemini 4 Argon
Time Horizon Index (Vals AI)52.5%Not measuredOnly Gemini 4 Argon measured
CUA-bench (Vals AI)4.8%Not measuredOnly Gemini 4 Argon measured
Robo-bench (Vals AI)0.8%Not measuredOnly Gemini 4 Argon measured
APEX-Agents82.4%44.3%Gemini 4 Argon
SpireClimbNot measured0.0%Only GPT-6 Luna measured
Vending-Bench 2$13,718Not measuredOnly Gemini 4 Argon measured
Neither model has a result on the other 17 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index110
Reasoning benchmarks for Gemini 4 Argon and GPT-6 Luna
BenchmarkGemini 4 ArgonGPT-6 LunaLeader
LiveBench reasoning95.1%81.8%Gemini 4 Argon
MysteryMechanism (Vals AI)45.5%19.4%Gemini 4 Argon
Humanity's Last Exam (Artificial Analysis run)57.1%38.5%Gemini 4 Argon
GPQA Diamond (Epoch AI run)96.4%90.5%Gemini 4 Argon
ARC-AGI98.5%86.7%Gemini 4 Argon
ARC-AGI-291.3%59.3%Gemini 4 Argon
Chess puzzles59.0%36.0%Gemini 4 Argon
Mystery game puzzles64.0%7.0%Gemini 4 Argon
EBR-bench64.8%Not measuredOnly Gemini 4 Argon measured
LMArena Text: hard prompts15461410Gemini 4 Argon
LMArena Text: expert15501442Gemini 4 Argon
LMArena Text: hard prompts in English15481410Gemini 4 Argon
LMArena Vision: diagramsNot measured1245Only GPT-6 Luna measured
LMArena Vision: homeworkNot measured1261Only GPT-6 Luna measured
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for Gemini 4 Argon and GPT-6 Luna
BenchmarkGemini 4 ArgonGPT-6 LunaLeader
OTIS Mock AIME100.0%98.9%Gemini 4 Argon
FrontierMath, tiers 1 to 386.0%78.9%Gemini 4 Argon
FrontierMath, tier 478.0%56.1%Gemini 4 Argon
ProofBench99.0%64.0%Gemini 4 Argon
LMArena Text: math15361409Gemini 4 Argon
LMArena Text: mathematical work15571427Gemini 4 Argon
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 Gemini 4 Argon and GPT-6 Luna
BenchmarkGemini 4 ArgonGPT-6 LunaLeader
LegalBench (Vals AI)88.3%Not measuredOnly Gemini 4 Argon measured
MedCode (Vals AI)58.8%44.7%Gemini 4 Argon
SimpleQA Verified76.0%41.4%Gemini 4 Argon
LMArena Text: science15481386Gemini 4 Argon
LMArena Text: medicine and healthcare15551352Gemini 4 Argon
LMArena Text: legal and government15481400Gemini 4 Argon
LMArena Text: business and finance15251388Gemini 4 Argon
Neither model has a result on the other 10 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index61
Web design benchmarks for Gemini 4 Argon and GPT-6 Luna
BenchmarkGemini 4 ArgonGPT-6 LunaLeader
Design Arena: websites13151272Gemini 4 Argon
Design Arena: UI components13331297Gemini 4 Argon
Design Arena: game dev13771259Gemini 4 Argon
Design Arena: data viz13341215Gemini 4 Argon
Design Arena: 3D13891217Gemini 4 Argon
Design Arena: all code categories13281271Gemini 4 Argon
Design Arena: SVGNot measured1253Only GPT-6 Luna measured
Design Arena: ASCII artNot measured1156Only GPT-6 Luna measured
LiveBench design73.7%82.5%GPT-6 Luna
GeneralLike-for-likePublic boards, shown as published, kept out of the index201
General benchmarks for Gemini 4 Argon and GPT-6 Luna
BenchmarkGemini 4 ArgonGPT-6 LunaLeader
Vals Index69.2%52.3%Gemini 4 Argon
LiveBench data analysis85.2%73.4%Gemini 4 Argon
Public Benefits Bench (Vals AI)69.8%57.6%Gemini 4 Argon
SAGE (Vals AI)53.6%48.1%Gemini 4 Argon
MedScribe (Vals AI)87.4%83.7%Gemini 4 Argon
Long context reasoning (AA-LCR)79.7%83.3%GPT-6 Luna
DTBench97.6%90.1%Gemini 4 Argon
LMCA63.7%44.5%Gemini 4 Argon
Furniture assembly72.5%44.2%Gemini 4 Argon
LMArena Text15321389Gemini 4 Argon
LMArena Text: instruction following15341408Gemini 4 Argon
LMArena Text: creative writing15271363Gemini 4 Argon
LMArena VisionNot measured1216Only GPT-6 Luna measured
LMArena Text: English15381393Gemini 4 Argon
LMArena Text: non-English15221381Gemini 4 Argon
LMArena Text: Chinese16111427Gemini 4 Argon
LMArena Text: GermanNot measured1376Only GPT-6 Luna measured
LMArena Text: JapaneseNot measured1369Only GPT-6 Luna measured
LMArena Text: KoreanNot measured1359Only GPT-6 Luna measured
LMArena Text: FrenchNot measured1408Only GPT-6 Luna measured
LMArena Text: Spanish15031391Gemini 4 Argon
LMArena Text: Russian15341392Gemini 4 Argon
LMArena Text: PolishNot measured1383Only GPT-6 Luna measured
LMArena Text: multi-turn15561392Gemini 4 Argon
LMArena Text: longer queries15471408Gemini 4 Argon
LMArena Text: writing and language15291384Gemini 4 Argon
LMArena Text: entertainment and media15271364Gemini 4 Argon
LMArena Vision: EnglishNot measured1204Only GPT-6 Luna measured
LMArena Vision: ChineseNot measured1266Only GPT-6 Luna measured
LMArena Vision: reading textNot measured1225Only GPT-6 Luna measured
LMArena Vision: creative writingNot measured1205Only GPT-6 Luna measured
Neither model has a result on the other 15 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemini 4 Argon and GPT-6 Luna
BenchmarkGemini 4 ArgonGPT-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

Gemini 4 Argon$0.0070Fits in one request
GPT-6 Luna$0.0003Fits in one request

GPT-6 Luna costs less

Repository review

50K input + 3K output tokens

Gemini 4 Argon$0.130Fits in one request
GPT-6 Luna$0.0065Fits in one request

GPT-6 Luna costs less

Agent loop

200K input + 10K output tokens

Gemini 4 Argon$0.500Fits 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 Gemini 4 Argon and GPT-6 Luna
SpecificationGoogle Gemini 4 ArgonOpenAI GPT-6 Luna
MakerGoogleOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedOctober 13, 2026September 22, 2026
Context window1.05M1.05M
Input $/Mtok$2.00$0.10
Output $/Mtok$10.00$0.50
Coding index80.571.4
Independent measurements behind it22
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 4 Argon better than GPT-6 Luna for coding?

Pick Gemini 4 Argon for coding: it scores 80.5 on the Vibe Coding Index against 71.4 for GPT-6 Luna. Pick GPT-6 Luna when output tokens cost 20.0x less, or when the context window is larger, 1.05M against 1.05M tokens.

Which is cheaper, Gemini 4 Argon or GPT-6 Luna?

Gemini 4 Argon costs $2.00 per million input tokens and $10.00 per million output tokens; GPT-6 Luna costs $0.10 and $0.50. Cost per solved task is known for neither of them.

Which has the bigger context window, Gemini 4 Argon or GPT-6 Luna?

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

How many benchmarks is the Gemini 4 Argon vs GPT-6 Luna comparison based on?

83 benchmarks have a result for both models as of October 21, 2026. Gemini 4 Argon's coding index rests on 2 independent benchmarks and GPT-6 Luna's on 2. 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/gemini-4-argon-vs-gpt-6-luna" title="Gemini 4 Argon 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/gemini-4-argon-vs-gpt-6-luna">LLMBenchmark.ai, Gemini 4 Argon vs GPT-6 Luna</a></p>