Enter opens the highlighted result. Esc closes.

Gemini 4 Argon vs Kimi K3

Gemini 4 Argon leads Kimi K3 on coding, 81.0 to 62.3 on the Vibe Coding Index, and Gemini 4 Argon costs 1.5x less per output token ($10.00 vs $15.00 per million). Updated October 22, 2026; 86 benchmarks have a result for both.

Replace Gemini 4 Argon Replace Kimi K3
Gemini 4 ArgonGoogle
Coding
81.0
Overall
84.0
Output $/M
$10.00
77
Kimi K3Moonshot AI
Coding
62.3
Overall
66.5
Output $/M
$15.00
9
vs boards won of 86 shared

Gemini 4 Argon or Kimi K3: which to pick

Pick Gemini 4 Argon for coding: it scores 81.0 on the Vibe Coding Index against 62.3 for Kimi K3, though on 5 benchmarks against 6.

Pick Kimi K3 for work measured by Terminal-Bench 2.1 (Vals AI) or LMArena WebDev: HTML, where it leads.

Model AGemini 4 ArgonGoogle81.0/1005 independent benchmarksNo cost per solved taskModel BKimi K3Moonshot AI62.3/1006 independent benchmarks$0.81 per solved task
Shared results
86
Gemini 4 Argon only
8
Kimi K3 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
Gemini 4 Argon 81.0 from 5 benchmarks, Kimi K3 62.3 from 6 benchmarks.
Widest category
Agentic work, 25.0 points apart on average over 14 shared benchmarks.
Widest single gap
LiveBench browser: Gemini 4 Argon 92.0% against Kimi K3 16.0%, 76.0 points apart on a 0 to 100 scale.
Output price
Gemini 4 Argon $10.00 against Kimi K3 $15.00 per million output tokens, 1.5x apart.
Context window
Both take 1.05M tokens.

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 ArgonBarsKimi K3Ties
Coding172
Intelligence20
Agentic work140
Reasoning100
Math60
Knowledge70
Web design25
General192
All shared boards779
CodingLike-for-likeSix of these boards feed the Vibe Coding Index172
Coding benchmarks for Gemini 4 Argon and Kimi K3
BenchmarkGemini 4 ArgonKimi K3Leader
LiveBench coding89.7%59.3%Gemini 4 Argon
LMArena WebDev16781655Gemini 4 Argon
AA Coding IndexNot measured76.2Only Kimi K3 measured
LiveCodeBench (Vals AI)Not measured87.2%Only Kimi K3 measured
SWE-bench Verified (Vals AI)Not measured93.4%Only Kimi K3 measured
Terminal-Bench 4 (Vals AI)57.6%17.2%Gemini 4 Argon
Vibe Code Bench (Vals AI)91.9%85.0%Gemini 4 Argon
Code migration (Vals AI)68.2%16.1%Gemini 4 Argon
ProgramBench (Vals AI)2.5%2.0%Gemini 4 Argon
IOI (Vals AI)100.0%48.9%Gemini 4 Argon
Terminal-Bench 2.1 (Vals AI)57.7%80.9%Kimi K3
SWE-bench Multimodal (Vals AI)56.0%44.2%Gemini 4 Argon
Vibe Code Bench 1-100 (Vals AI)21.2%18.2%Gemini 4 Argon
CyberBench (Vals AI)77.9%75.2%Gemini 4 Argon
SciCode61.8%59.5%Gemini 4 Argon
FrontierCode47.5%44.2%Gemini 4 Argon
FrontierSWE55.0%25.9%Gemini 4 Argon
WeirdMLNot measured82.6%Only Kimi K3 measured
MirrorCode58.9%Not measuredOnly Gemini 4 Argon measured
ALE-Bench2100.11524.5Gemini 4 Argon
LMArena Text: coding15461508Gemini 4 Argon
LMArena Text: software and IT15561499Gemini 4 Argon
LMArena WebDev: React16921670Gemini 4 Argon
LMArena WebDev: HTML16431644Kimi K3
LMArena WebDev: from an imageNot measured1579Only Kimi K3 measured
SciCode12.3%Not measuredOnly Gemini 4 Argon measured
Neither model has a result on the other 13 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Gemini 4 Argon and Kimi K3
BenchmarkGemini 4 ArgonKimi K3Leader
AA Intelligence Index52.643.6Gemini 4 Argon
Epoch Capabilities Index166.4157.9Gemini 4 Argon
Agentic workLike-for-likePublic boards, shown as published, kept out of the index140
Agentic work benchmarks for Gemini 4 Argon and Kimi K3
BenchmarkGemini 4 ArgonKimi K3Leader
AA Agentic IndexNot measured50.0Only Kimi K3 measured
Design Arena: agents building web appsNot measured1295Only Kimi K3 measured
Design Arena: agents building full-stack appsNot measured1315Only Kimi K3 measured
Design Arena: agents building mobile appsNot measured1269Only Kimi K3 measured
Design Arena: agents building Android appsNot measured1253Only Kimi K3 measured
Design Arena: agents building Godot gamesNot measured1223Only Kimi K3 measured
Design Arena: agents building gamesNot measured1252Only Kimi K3 measured
Design Arena: HTML slidesNot measured1206Only Kimi K3 measured
Design Arena: PowerPoint slidesNot measured1247Only Kimi K3 measured
Design Arena: spreadsheets11571070Gemini 4 Argon
LiveBench research83.1%79.0%Gemini 4 Argon
LiveBench browser92.0%16.0%Gemini 4 Argon
LiveBench long agentic69.9%42.8%Gemini 4 Argon
SREBench (Vals AI)44.3%Not measuredOnly Gemini 4 Argon measured
Finance Agent (Vals AI)65.4%53.1%Gemini 4 Argon
Tax Agent Bench (Vals AI)44.6%33.4%Gemini 4 Argon
Legal Research Bench (Vals AI)54.8%46.1%Gemini 4 Argon
Harvey's Legal Agent Benchmark (Vals AI)27.1%12.9%Gemini 4 Argon
Excel Modeling Benchmark (Vals AI)75.2%66.7%Gemini 4 Argon
BioMysteryBench (Vals AI)76.3%72.6%Gemini 4 Argon
Terminal-Bench-Science (Vals AI)44.3%1.4%Gemini 4 Argon
Vals Science Index55.4%Not measuredOnly Gemini 4 Argon measured
Time Horizon Index (Vals AI)52.5%10.5%Gemini 4 Argon
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%47.8%Gemini 4 Argon
PostTrainBenchNot measured32.0%Only Kimi K3 measured
Vending-Bench 2$13,718$5,165Gemini 4 Argon
Neither model has a result on the other 13 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index100
Reasoning benchmarks for Gemini 4 Argon and Kimi K3
BenchmarkGemini 4 ArgonKimi K3Leader
GPQA DiamondNot measured92.9%Only Kimi K3 measured
LiveBench reasoning95.1%90.7%Gemini 4 Argon
MysteryMechanism (Vals AI)45.5%Not measuredOnly Gemini 4 Argon measured
MMMU Pro (Vals AI)Not measured88.2%Only Kimi K3 measured
GPQA Diamond (Artificial Analysis run)Not measured93.5%Only Kimi K3 measured
Humanity's Last Exam (Artificial Analysis run)57.1%46.9%Gemini 4 Argon
GPQA Diamond (Epoch AI run)96.4%93.1%Gemini 4 Argon
ARC-AGI98.5%94.5%Gemini 4 Argon
ARC-AGI-291.3%60.4%Gemini 4 Argon
SimpleBenchNot measured60.7%Only Kimi K3 measured
Chess puzzles59.0%37.0%Gemini 4 Argon
Mystery game puzzles64.0%26.0%Gemini 4 Argon
EBR-bench64.8%Not measuredOnly Gemini 4 Argon measured
LMArena Text: hard prompts15461495Gemini 4 Argon
LMArena Text: expert15501520Gemini 4 Argon
LMArena Text: hard prompts in English15481496Gemini 4 Argon
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for Gemini 4 Argon and Kimi K3
BenchmarkGemini 4 ArgonKimi K3Leader
OTIS Mock AIME100.0%97.2%Gemini 4 Argon
FrontierMath, tiers 1 to 386.0%72.2%Gemini 4 Argon
FrontierMath, tier 478.0%39.0%Gemini 4 Argon
ProofBench99.0%87.0%Gemini 4 Argon
LMArena Text: math15361494Gemini 4 Argon
LMArena Text: mathematical work15571505Gemini 4 Argon
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index70
Knowledge benchmarks for Gemini 4 Argon and Kimi K3
BenchmarkGemini 4 ArgonKimi K3Leader
MMLU ProNot measured88.0%Only Kimi K3 measured
LegalBench (Vals AI)88.3%86.2%Gemini 4 Argon
CorpFin (Vals AI)Not measured71.6%Only Kimi K3 measured
TaxEval (Vals AI)Not measured75.7%Only Kimi K3 measured
MortgageTax (Vals AI)Not measured66.3%Only Kimi K3 measured
MedCode (Vals AI)58.8%49.4%Gemini 4 Argon
SimpleQA Verified76.0%50.6%Gemini 4 Argon
LMArena Text: science15481508Gemini 4 Argon
LMArena Text: medicine and healthcare15551489Gemini 4 Argon
LMArena Text: legal and government15481503Gemini 4 Argon
LMArena Text: business and finance15251470Gemini 4 Argon
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index25
Web design benchmarks for Gemini 4 Argon and Kimi K3
BenchmarkGemini 4 ArgonKimi K3Leader
Design Arena: websites13151334Kimi K3
Design Arena: UI components13331341Kimi K3
Design Arena: game dev13771358Gemini 4 Argon
Design Arena: data viz13321351Kimi K3
Design Arena: 3D13881387Gemini 4 Argon
Design Arena: all code categories13291360Kimi K3
Design Arena: SVGNot measured1302Only Kimi K3 measured
LiveBench design73.7%77.2%Kimi K3
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index192
General benchmarks for Gemini 4 Argon and Kimi K3
BenchmarkGemini 4 ArgonKimi K3Leader
Vals Index69.2%53.0%Gemini 4 Argon
LiveBench data analysis85.2%78.7%Gemini 4 Argon
Public Benefits Bench (Vals AI)69.8%68.2%Gemini 4 Argon
SAGE (Vals AI)53.6%52.8%Gemini 4 Argon
MedScribe (Vals AI)87.4%88.0%Kimi K3
Vals Multimodal IndexNot measured73.4%Only Kimi K3 measured
Long context reasoning (AA-LCR)79.7%88.7%Kimi K3
DTBench97.6%91.2%Gemini 4 Argon
LMCA63.7%52.7%Gemini 4 Argon
Surface Evolver BenchNot measured95.0%Only Kimi K3 measured
Furniture assembly72.5%34.2%Gemini 4 Argon
LMArena Text15321476Gemini 4 Argon
LMArena Text: instruction following15341485Gemini 4 Argon
LMArena Text: creative writing15271457Gemini 4 Argon
LMArena Text: English15381481Gemini 4 Argon
LMArena Text: non-English15221466Gemini 4 Argon
LMArena Text: Chinese16111529Gemini 4 Argon
LMArena Text: GermanNot measured1490Only Kimi K3 measured
LMArena Text: JapaneseNot measured1494Only Kimi K3 measured
LMArena Text: KoreanNot measured1460Only Kimi K3 measured
LMArena Text: FrenchNot measured1492Only Kimi K3 measured
LMArena Text: Spanish15031472Gemini 4 Argon
LMArena Text: Russian15341485Gemini 4 Argon
LMArena Text: PolishNot measured1458Only Kimi K3 measured
LMArena Text: multi-turn15561489Gemini 4 Argon
LMArena Text: longer queries15471494Gemini 4 Argon
LMArena Text: writing and language15291471Gemini 4 Argon
LMArena Text: entertainment and media15271453Gemini 4 Argon
Neither model has a result on the other 18 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 Kimi K3
BenchmarkGemini 4 ArgonKimi K3Leader
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
Kimi K3$0.011Fits in one request

Gemini 4 Argon costs less

Repository review

50K input + 3K output tokens

Gemini 4 Argon$0.130Fits in one request
Kimi K3$0.195Fits in one request

Gemini 4 Argon costs less

Agent loop

200K input + 10K output tokens

Gemini 4 Argon$0.500Fits in one request
Kimi K3$0.750Fits in one request

Gemini 4 Argon 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 Kimi K3
SpecificationGoogle Gemini 4 ArgonMoonshotAI Kimi K3
MakerGoogleMoonshot AI
WeightsNo public weights listedOpen weights
ReleasedOctober 13, 2026July 16, 2026
Context window1.05M1.05M
Input $/Mtok$2.00$3.00
Output $/Mtok$10.00$15.00
Coding index81.062.3
Independent measurements behind it56
Cost per solved taskNot computable$0.81
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 4 Argon better than Kimi K3 for coding?

Pick Gemini 4 Argon for coding: it scores 81.0 on the Vibe Coding Index against 62.3 for Kimi K3, though on 5 benchmarks against 6. Pick Kimi K3 for work measured by Terminal-Bench 2.1 (Vals AI) or LMArena WebDev: HTML, where it leads.

Which is cheaper, Gemini 4 Argon or Kimi K3?

Gemini 4 Argon costs $2.00 per million input tokens and $10.00 per million output tokens; Kimi K3 costs $3.00 and $15.00. Cost per solved task is known for Kimi K3 only.

Which has the bigger context window, Gemini 4 Argon or Kimi K3?

Neither: both take 1.05M tokens.

How many benchmarks is the Gemini 4 Argon vs Kimi K3 comparison based on?

86 benchmarks have a result for both models as of October 22, 2026. Gemini 4 Argon's coding index rests on 5 independent benchmarks and Kimi K3'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/gemini-4-argon-vs-kimi-k3" title="Gemini 4 Argon vs Kimi K3, 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-kimi-k3">LLMBenchmark.ai, Gemini 4 Argon vs Kimi K3</a></p>