Enter opens the highlighted result. Esc closes.

Gemini 4 Argon vs Inkling 2 Mini

Gemini 4 Argon leads Inkling 2 Mini on coding, 80.3 to 39.5 on the Vibe Coding Index, and Inkling 2 Mini costs 30.8x less per output token ($0.325 vs $10.00 per million). Updated November 22, 2026; 28 benchmarks have a result for both.

Gemini 4 ArgonGoogle
Coding
80.3
Overall
82.4
Output $/M
$10.00
28
T Inkling 2 MiniThinking Machines
Coding
39.5
Overall
No data
Output $/M
$0.325
0
vs boards won of 28 shared

Gemini 4 Argon or Inkling 2 Mini: which to pick

Pick Gemini 4 Argon for coding: it scores 80.3 on the Vibe Coding Index against 39.5 for Inkling 2 Mini.

Pick Inkling 2 Mini for output tokens 30.8x cheaper ($0.325 vs $10.00 per million).

Shared results
28
Gemini 4 Argon only
97
Inkling 2 Mini only
1
Like-for-like categories
7 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 80.3 from 5 benchmarks, Inkling 2 Mini 39.5 from 2 benchmarks.
Widest category
Agentic work, 34.7 points apart on average over 7 shared benchmarks.
Widest single gap
IOI (Vals AI): Gemini 4 Argon 100.0% against Inkling 2 Mini 11.6%, 88.4 points apart on a 0 to 100 scale.
Output price
Gemini 4 Argon $10.00 against Inkling 2 Mini $0.325 per million output tokens, 30.8x 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 ArgonBarsInkling 2 MiniTies
Coding80
Intelligence10
Agentic work70
Reasoning30
Knowledge20
Web design30
General40
All shared boards280
CodingLike-for-likeSix of these boards feed the Vibe Coding Index80
Coding benchmarks for Gemini 4 Argon and Inkling 2 Mini
BenchmarkGemini 4 ArgonInkling 2 MiniLeader
LiveBench coding85.7%Not measuredOnly Gemini 4 Argon measured
LMArena WebDev1682Not measuredOnly Gemini 4 Argon measured
Terminal-Bench 4 (Vals AI)57.6%6.6%Gemini 4 Argon
Vibe Code Bench (Vals AI)91.9%77.9%Gemini 4 Argon
Code migration (Vals AI)68.2%Not measuredOnly Gemini 4 Argon measured
ProgramBench (Vals AI)2.5%0.5%Gemini 4 Argon
IOI (Vals AI)100.0%11.6%Gemini 4 Argon
Terminal-Bench 2.1 (Vals AI)57.7%Not measuredOnly Gemini 4 Argon measured
SWE-bench Multimodal (Vals AI)56.0%37.9%Gemini 4 Argon
Vibe Code Bench 1-100 (Vals AI)21.2%Not measuredOnly Gemini 4 Argon measured
SkillsBench (Vals AI)Not measured43.2%Only Inkling 2 Mini measured
CyberBench (Vals AI)77.9%74.6%Gemini 4 Argon
SciCode61.8%Not measuredOnly Gemini 4 Argon measured
Terminal-Bench 4.0 (Artificial Analysis run)57.1%5.6%Gemini 4 Argon
FrontierCode 2.025.7%15.1%Gemini 4 Argon
FrontierCode47.5%Not measuredOnly Gemini 4 Argon measured
FrontierSWE55.0%Not measuredOnly Gemini 4 Argon measured
MirrorCode58.9%Not measuredOnly Gemini 4 Argon measured
ALE-Bench2100.1Not measuredOnly Gemini 4 Argon measured
LMArena Text: coding1539Not measuredOnly Gemini 4 Argon measured
LMArena Text: software and IT1542Not measuredOnly Gemini 4 Argon measured
LMArena WebDev: React1701Not measuredOnly Gemini 4 Argon measured
LMArena WebDev: HTML1678Not measuredOnly Gemini 4 Argon measured
SciCode12.3%Not measuredOnly Gemini 4 Argon measured
SWE-Bench Pro V299.2%Not measuredOnly Gemini 4 Argon measured
GameBench 289.1Not measuredOnly Gemini 4 Argon measured
Terminal-Bench 4.054.9%Not measuredOnly Gemini 4 Argon measured
CursorBench 4.056.5%Not measuredOnly Gemini 4 Argon measured
Neither model has a result on the other 24 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Gemini 4 Argon and Inkling 2 Mini
BenchmarkGemini 4 ArgonInkling 2 MiniLeader
AA Intelligence Index50.420.1Gemini 4 Argon
Epoch Capabilities Index166.5Not measuredOnly Gemini 4 Argon measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index70
Agentic work benchmarks for Gemini 4 Argon and Inkling 2 Mini
BenchmarkGemini 4 ArgonInkling 2 MiniLeader
Design Arena: agents building web apps1276Not measuredOnly Gemini 4 Argon measured
Design Arena: agents building mobile apps1230Not measuredOnly Gemini 4 Argon measured
Design Arena: agents building games1266Not measuredOnly Gemini 4 Argon measured
Design Arena: spreadsheets1146Not measuredOnly Gemini 4 Argon measured
LiveBench research86.8%Not measuredOnly Gemini 4 Argon measured
LiveBench browser82.8%Not measuredOnly Gemini 4 Argon measured
LiveBench long agentic58.5%Not measuredOnly Gemini 4 Argon measured
SREBench (Vals AI)44.3%0.0%Gemini 4 Argon
Finance Agent (Vals AI)65.4%Not measuredOnly Gemini 4 Argon measured
Tax Agent Bench (Vals AI)49.2%14.1%Gemini 4 Argon
Legal Research Bench (Vals AI)54.8%17.8%Gemini 4 Argon
Harvey's Legal Agent Benchmark (Vals AI)27.1%5.0%Gemini 4 Argon
Excel Modeling Benchmark (Vals AI)75.2%Not measuredOnly Gemini 4 Argon measured
BioMysteryBench (Vals AI)76.3%47.8%Gemini 4 Argon
Terminal-Bench-Science (Vals AI)44.3%0.0%Gemini 4 Argon
Vals Science Index55.4%23.6%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%Not measuredOnly Gemini 4 Argon measured
Remote Labor Index17.1%Not measuredOnly Gemini 4 Argon measured
PostTrainBench40.4%Not measuredOnly Gemini 4 Argon measured
Vending-Bench 2$13,718Not measuredOnly Gemini 4 Argon measured
MCP Atlas90.7%Not measuredOnly Gemini 4 Argon measured
Neither model has a result on the other 20 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index30
Reasoning benchmarks for Gemini 4 Argon and Inkling 2 Mini
BenchmarkGemini 4 ArgonInkling 2 MiniLeader
LiveBench reasoning95.1%Not measuredOnly Gemini 4 Argon measured
MysteryMechanism (Vals AI)45.5%23.0%Gemini 4 Argon
Humanity's Last Exam (Artificial Analysis run)57.1%Not measuredOnly Gemini 4 Argon measured
HLE-Diamond (Artificial Analysis run)56.7%15.2%Gemini 4 Argon
CritPt v2, hard subset (Artificial Analysis run)53.5%17.0%Gemini 4 Argon
GPQA Diamond (Epoch AI run)96.4%Not measuredOnly Gemini 4 Argon measured
ARC-AGI98.5%Not measuredOnly Gemini 4 Argon measured
ARC-AGI-291.3%Not measuredOnly Gemini 4 Argon measured
SimpleBench91.7%Not measuredOnly Gemini 4 Argon measured
Chess puzzles59.0%Not measuredOnly Gemini 4 Argon measured
Mystery game puzzles64.0%Not measuredOnly Gemini 4 Argon measured
EBR-bench64.8%Not measuredOnly Gemini 4 Argon measured
LMArena Text: hard prompts1542Not measuredOnly Gemini 4 Argon measured
LMArena Text: expert1556Not measuredOnly Gemini 4 Argon measured
LMArena Text: hard prompts in English1538Not measuredOnly Gemini 4 Argon measured
Humanity's Last Exam (Scale run)53.2%Not measuredOnly Gemini 4 Argon measured
GoBench2350Not measuredOnly Gemini 4 Argon measured
Neither model has a result on the other 9 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Math benchmarks for Gemini 4 Argon and Inkling 2 Mini
BenchmarkGemini 4 ArgonInkling 2 MiniLeader
OTIS Mock AIME100.0%Not measuredOnly Gemini 4 Argon measured
FrontierMath, tiers 1 to 386.0%Not measuredOnly Gemini 4 Argon measured
FrontierMath, tier 478.0%Not measuredOnly Gemini 4 Argon measured
ProofBench99.0%Not measuredOnly Gemini 4 Argon measured
LMArena Text: math1543Not measuredOnly Gemini 4 Argon measured
LMArena Text: mathematical work1554Not measuredOnly Gemini 4 Argon measured
MathArena62.1%Not measuredOnly Gemini 4 Argon measured
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index20
Knowledge benchmarks for Gemini 4 Argon and Inkling 2 Mini
BenchmarkGemini 4 ArgonInkling 2 MiniLeader
LegalBench (Vals AI)88.3%Not measuredOnly Gemini 4 Argon measured
MedCode (Vals AI)58.8%25.7%Gemini 4 Argon
AA-Omniscience46.1-8.6Gemini 4 Argon
SimpleQA Verified76.0%Not measuredOnly Gemini 4 Argon measured
LMArena Text: science1549Not measuredOnly Gemini 4 Argon measured
LMArena Text: medicine and healthcare1538Not measuredOnly Gemini 4 Argon measured
LMArena Text: legal and government1541Not measuredOnly Gemini 4 Argon measured
LMArena Text: business and finance1518Not measuredOnly Gemini 4 Argon measured
FACTS Benchmark Suite72.4%Not measuredOnly Gemini 4 Argon measured
PRBench Finance49.9%Not measuredOnly Gemini 4 Argon measured
PRBench Legal49.9%Not measuredOnly Gemini 4 Argon measured
Neither model has a result on the other 10 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index30
Web design benchmarks for Gemini 4 Argon and Inkling 2 Mini
BenchmarkGemini 4 ArgonInkling 2 MiniLeader
Design Arena: websites1312Not measuredOnly Gemini 4 Argon measured
Design Arena: UI components13251292Gemini 4 Argon
Design Arena: game dev13471287Gemini 4 Argon
Design Arena: data viz1322Not measuredOnly Gemini 4 Argon measured
Design Arena: 3D13411308Gemini 4 Argon
Design Arena: all code categories1319Not measuredOnly Gemini 4 Argon measured
Design Arena: SVG1332Not measuredOnly Gemini 4 Argon measured
LiveBench design69.2%Not measuredOnly Gemini 4 Argon measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index40
General benchmarks for Gemini 4 Argon and Inkling 2 Mini
BenchmarkGemini 4 ArgonInkling 2 MiniLeader
Vals Index69.4%46.5%Gemini 4 Argon
LiveBench data analysis85.2%Not measuredOnly Gemini 4 Argon measured
Public Benefits Bench (Vals AI)69.8%Not measuredOnly Gemini 4 Argon measured
SAGE (Vals AI)89.5%85.9%Gemini 4 Argon
MedScribe (Vals AI)87.4%86.4%Gemini 4 Argon
Long context reasoning (AA-LCR)79.7%Not measuredOnly Gemini 4 Argon measured
GDPval-AA16341319Gemini 4 Argon
DTBench97.6%Not measuredOnly Gemini 4 Argon measured
LMCA63.7%Not measuredOnly Gemini 4 Argon measured
Furniture assembly72.5%Not measuredOnly Gemini 4 Argon measured
LMArena Text1528Not measuredOnly Gemini 4 Argon measured
LMArena Text: instruction following1535Not measuredOnly Gemini 4 Argon measured
LMArena Text: creative writing1531Not measuredOnly Gemini 4 Argon measured
LMArena Text: English1527Not measuredOnly Gemini 4 Argon measured
LMArena Text: non-English1521Not measuredOnly Gemini 4 Argon measured
LMArena Text: Chinese1608Not measuredOnly Gemini 4 Argon measured
LMArena Text: German1585Not measuredOnly Gemini 4 Argon measured
LMArena Text: Japanese1532Not measuredOnly Gemini 4 Argon measured
LMArena Text: Korean1505Not measuredOnly Gemini 4 Argon measured
LMArena Text: French1551Not measuredOnly Gemini 4 Argon measured
LMArena Text: Spanish1516Not measuredOnly Gemini 4 Argon measured
LMArena Text: Russian1539Not measuredOnly Gemini 4 Argon measured
LMArena Text: Polish1547Not measuredOnly Gemini 4 Argon measured
LMArena Text: multi-turn1545Not measuredOnly Gemini 4 Argon measured
LMArena Text: longer queries1544Not measuredOnly Gemini 4 Argon measured
LMArena Text: writing and language1530Not measuredOnly Gemini 4 Argon measured
LMArena Text: entertainment and media1522Not measuredOnly Gemini 4 Argon measured
MultiChallenge78.7%Not measuredOnly Gemini 4 Argon measured
EQ-Bench 41236Not measuredOnly Gemini 4 Argon measured
Neither model has a result on the other 20 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 Inkling 2 Mini
BenchmarkGemini 4 ArgonInkling 2 MiniLeader
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
Inkling 2 Mini$0.0002Fits in one request

Inkling 2 Mini costs less

Repository review

50K input + 3K output tokens

Gemini 4 Argon$0.130Fits in one request
Inkling 2 Mini$0.0049Fits in one request

Inkling 2 Mini costs less

Agent loop

200K input + 10K output tokens

Gemini 4 Argon$0.500Fits in one request
Inkling 2 Mini$0.019Fits in one request

Inkling 2 Mini 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 Inkling 2 Mini
SpecificationGoogle Gemini 4 ArgonThinking Machines Inkling 2 Mini
MakerGoogleThinking Machines
WeightsNo public weights listedOpen weights
ReleasedOctober 13, 2026November 21, 2026
Context window1.05M1.05M
Input $/Mtok$2.00$0.0775
Output $/Mtok$10.00$0.325
Coding index80.339.5
Independent measurements behind it52
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 4 Argon better than Inkling 2 Mini for coding?

Pick Gemini 4 Argon for coding: it scores 80.3 on the Vibe Coding Index against 39.5 for Inkling 2 Mini. Pick Inkling 2 Mini for output tokens 30.8x cheaper ($0.325 vs $10.00 per million).

Which is cheaper, Gemini 4 Argon or Inkling 2 Mini?

Gemini 4 Argon costs $2.00 per million input tokens and $10.00 per million output tokens; Inkling 2 Mini costs $0.0775 and $0.325. Cost per solved task is known for neither of them.

Which has the bigger context window, Gemini 4 Argon or Inkling 2 Mini?

Neither: both take 1.05M tokens.

How many benchmarks is the Gemini 4 Argon vs Inkling 2 Mini comparison based on?

28 benchmarks have a result for both models as of November 22, 2026. Gemini 4 Argon's coding index rests on 5 independent benchmarks and Inkling 2 Mini'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-thinkingmachines-inkling-2-mini" title="Gemini 4 Argon vs Inkling 2 Mini, 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-thinkingmachines-inkling-2-mini">LLMBenchmark.ai, Gemini 4 Argon vs Inkling 2 Mini</a></p>