Enter opens the highlighted result. Esc closes.

Gemini 3.1 Pro Preview vs Inkling 2 Mini

Inkling 2 Mini leads Gemini 3.1 Pro Preview on coding, 39.5 to 32.3 on the Vibe Coding Index, and Inkling 2 Mini costs 36.9x less per output token ($0.325 vs $12.00 per million). Updated November 22, 2026; 20 benchmarks have a result for both.

Gemini 3.1 Pro PreviewGoogle
Coding
32.3
Overall
66.5
Output $/M
$12.00
7
T Inkling 2 MiniThinking Machines
Coding
39.5
Overall
No data
Output $/M
$0.325
12
vs boards won of 20 shared, 1 tied

Gemini 3.1 Pro Preview or Inkling 2 Mini: which to pick

Pick Inkling 2 Mini for coding: it scores 39.5 on the Vibe Coding Index against 32.3 for Gemini 3.1 Pro Preview, though on 2 benchmarks against 4.

Pick Gemini 3.1 Pro Preview for work measured by IOI (Vals AI) or Legal Research Bench (Vals AI), where it leads.

Shared results
20
Gemini 3.1 Pro Preview only
119
Inkling 2 Mini only
9
Like-for-like categories
6 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 3.1 Pro Preview 32.3 from 4 benchmarks, Inkling 2 Mini 39.5 from 2 benchmarks.
Widest category
Knowledge, 33.4 points apart on average over 1 shared benchmark.
Widest single gap
Vibe Code Bench (Vals AI): Gemini 3.1 Pro Preview 32.0% against Inkling 2 Mini 77.9%, 45.9 points apart on a 0 to 100 scale.
Output price
Gemini 3.1 Pro Preview $12.00 against Inkling 2 Mini $0.325 per million output tokens, 36.9x 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 3.1 Pro PreviewBarsInkling 2 MiniTies
Coding14
Agentic work411 tie
Reasoning11
Knowledge10
Web design03
General03
All shared boards7121 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index14
Coding benchmarks for Gemini 3.1 Pro Preview and Inkling 2 Mini
BenchmarkGemini 3.1 Pro PreviewInkling 2 MiniLeader
LMArena WebDev1446Not measuredOnly Gemini 3.1 Pro Preview measured
LiveCodeBench (Vals AI)88.5%Not measuredOnly Gemini 3.1 Pro Preview measured
SWE-bench Verified (Vals AI)78.8%Not measuredOnly Gemini 3.1 Pro Preview measured
Terminal-Bench 4 (Vals AI)2.5%6.6%Inkling 2 Mini
Vibe Code Bench (Vals AI)32.0%77.9%Inkling 2 Mini
Code migration (Vals AI)17.3%Not measuredOnly Gemini 3.1 Pro Preview measured
ProgramBench (Vals AI)0.0%0.5%Inkling 2 Mini
IOI (Vals AI)51.8%11.6%Gemini 3.1 Pro Preview
Terminal-Bench 2.1 (Vals AI)70.8%Not measuredOnly Gemini 3.1 Pro Preview measured
SWE-bench Multimodal (Vals AI)Not measured37.9%Only Inkling 2 Mini measured
Vibe Code Bench 1-100 (Vals AI)6.7%Not measuredOnly Gemini 3.1 Pro Preview measured
SkillsBench (Vals AI)Not measured43.2%Only Inkling 2 Mini measured
CyberBench (Vals AI)Not measured74.6%Only Inkling 2 Mini measured
SciCode58.7%Not measuredOnly Gemini 3.1 Pro Preview measured
Terminal-Bench Hard (Artificial Analysis run)53.8%Not measuredOnly Gemini 3.1 Pro Preview measured
Terminal-Bench 4.0 (Artificial Analysis run)4.0%5.6%Inkling 2 Mini
FrontierCode 2.0Not measured15.1%Only Inkling 2 Mini measured
Terminal-Bench80.2%Not measuredOnly Gemini 3.1 Pro Preview measured
GSO-Bench22.6%Not measuredOnly Gemini 3.1 Pro Preview measured
WeirdML72.1%Not measuredOnly Gemini 3.1 Pro Preview measured
MirrorCode8.9%Not measuredOnly Gemini 3.1 Pro Preview measured
ALE-Bench1160.6Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: coding1483Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: software and IT1486Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena WebDev: React1437Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena WebDev: HTML1488Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena WebDev: from an image1480Not measuredOnly Gemini 3.1 Pro Preview measured
SciCode14.3%Not measuredOnly Gemini 3.1 Pro Preview measured
GameBench 264.7Not measuredOnly Gemini 3.1 Pro Preview measured
Neither model has a result on the other 23 boards here
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
Intelligence benchmarks for Gemini 3.1 Pro Preview and Inkling 2 Mini
BenchmarkGemini 3.1 Pro PreviewInkling 2 MiniLeader
AA Intelligence IndexNot measured20.1Only Inkling 2 Mini measured
Neither model has a result on the other 1 board here
Agentic workLike-for-likePublic boards, shown as published, kept out of the index41
Agentic work benchmarks for Gemini 3.1 Pro Preview and Inkling 2 Mini
BenchmarkGemini 3.1 Pro PreviewInkling 2 MiniLeader
Design Arena: agents building web apps1093Not measuredOnly Gemini 3.1 Pro Preview measured
Design Arena: agents building full-stack apps1045Not measuredOnly Gemini 3.1 Pro Preview measured
Design Arena: agents building mobile apps1086Not measuredOnly Gemini 3.1 Pro Preview measured
Design Arena: agents building Android apps1033Not measuredOnly Gemini 3.1 Pro Preview measured
Design Arena: agents building Godot games1124Not measuredOnly Gemini 3.1 Pro Preview measured
Design Arena: agents building games1061Not measuredOnly Gemini 3.1 Pro Preview measured
Design Arena: HTML slides1054Not measuredOnly Gemini 3.1 Pro Preview measured
Design Arena: PowerPoint slides1047Not measuredOnly Gemini 3.1 Pro Preview measured
Design Arena: spreadsheets918Not measuredOnly Gemini 3.1 Pro Preview measured
SREBench (Vals AI)0.0%0.0%Tie
Finance Agent (Vals AI)43.0%Not measuredOnly Gemini 3.1 Pro Preview measured
Tax Agent Bench (Vals AI)9.3%14.1%Inkling 2 Mini
Legal Research Bench (Vals AI)20.7%17.8%Gemini 3.1 Pro Preview
Harvey's Legal Agent Benchmark (Vals AI)Not measured5.0%Only Inkling 2 Mini measured
Excel Modeling Benchmark (Vals AI)52.6%Not measuredOnly Gemini 3.1 Pro Preview measured
BioMysteryBench (Vals AI)60.0%47.8%Gemini 3.1 Pro Preview
Terminal-Bench-Science (Vals AI)1.4%0.0%Gemini 3.1 Pro Preview
Vals Science Index27.4%23.6%Gemini 3.1 Pro Preview
τ²-Bench Telecom95.6%Not measuredOnly Gemini 3.1 Pro Preview measured
APEX-Agents35.1%Not measuredOnly Gemini 3.1 Pro Preview measured
METR time horizons77.0%Not measuredOnly Gemini 3.1 Pro Preview measured
BALROG57.0%Not measuredOnly Gemini 3.1 Pro Preview measured
DeepResearch Bench47.8%Not measuredOnly Gemini 3.1 Pro Preview measured
PostTrainBench18.1%Not measuredOnly Gemini 3.1 Pro Preview measured
Vending-Bench 2$911Not measuredOnly Gemini 3.1 Pro Preview measured
τ³-Banking26.0%Not measuredOnly Gemini 3.1 Pro Preview measured
Neither model has a result on the other 18 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index11
Reasoning benchmarks for Gemini 3.1 Pro Preview and Inkling 2 Mini
BenchmarkGemini 3.1 Pro PreviewInkling 2 MiniLeader
GPQA Diamond95.5%Not measuredOnly Gemini 3.1 Pro Preview measured
MysteryMechanism (Vals AI)20.7%23.0%Inkling 2 Mini
MMMU Pro (Vals AI)88.2%Not measuredOnly Gemini 3.1 Pro Preview measured
GPQA Diamond (Artificial Analysis run)94.1%Not measuredOnly Gemini 3.1 Pro Preview measured
Humanity's Last Exam (Artificial Analysis run)47.0%Not measuredOnly Gemini 3.1 Pro Preview measured
HLE-Diamond (Artificial Analysis run)31.4%15.2%Gemini 3.1 Pro Preview
CritPt v2, hard subset (Artificial Analysis run)Not measured17.0%Only Inkling 2 Mini measured
GPQA Diamond (Epoch AI run)94.4%Not measuredOnly Gemini 3.1 Pro Preview measured
ARC-AGI98.0%Not measuredOnly Gemini 3.1 Pro Preview measured
ARC-AGI-277.1%Not measuredOnly Gemini 3.1 Pro Preview measured
SimpleBench79.6%Not measuredOnly Gemini 3.1 Pro Preview measured
Chess puzzles51.0%Not measuredOnly Gemini 3.1 Pro Preview measured
Mystery game puzzles34.0%Not measuredOnly Gemini 3.1 Pro Preview measured
EBR-bench14.3%Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: hard prompts1485Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: expert1484Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: hard prompts in English1480Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Vision: diagrams1311Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Vision: homework1317Not measuredOnly Gemini 3.1 Pro Preview measured
Neither model has a result on the other 7 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Math benchmarks for Gemini 3.1 Pro Preview and Inkling 2 Mini
BenchmarkGemini 3.1 Pro PreviewInkling 2 MiniLeader
AIME98.1%Not measuredOnly Gemini 3.1 Pro Preview measured
OTIS Mock AIME95.6%Not measuredOnly Gemini 3.1 Pro Preview measured
FrontierMath, tiers 1 to 359.6%Not measuredOnly Gemini 3.1 Pro Preview measured
FrontierMath, tier 426.8%Not measuredOnly Gemini 3.1 Pro Preview measured
ProofBench26.0%Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: math1485Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: mathematical work1477Not measuredOnly Gemini 3.1 Pro Preview measured
MathArena27.3%Not measuredOnly Gemini 3.1 Pro Preview measured
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
Knowledge benchmarks for Gemini 3.1 Pro Preview and Inkling 2 Mini
BenchmarkGemini 3.1 Pro PreviewInkling 2 MiniLeader
MMLU Pro91.0%Not measuredOnly Gemini 3.1 Pro Preview measured
LegalBench (Vals AI)87.4%Not measuredOnly Gemini 3.1 Pro Preview measured
CaseLaw (Vals AI)64.8%Not measuredOnly Gemini 3.1 Pro Preview measured
CorpFin (Vals AI)64.5%Not measuredOnly Gemini 3.1 Pro Preview measured
TaxEval (Vals AI)72.9%Not measuredOnly Gemini 3.1 Pro Preview measured
MortgageTax (Vals AI)69.4%Not measuredOnly Gemini 3.1 Pro Preview measured
MedQA (Vals AI)96.4%Not measuredOnly Gemini 3.1 Pro Preview measured
MedCode (Vals AI)59.1%25.7%Gemini 3.1 Pro Preview
AA-OmniscienceNot measured-8.6Only Inkling 2 Mini measured
SimpleQA Verified73.5%Not measuredOnly Gemini 3.1 Pro Preview measured
GeoBench84.0%Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: science1496Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: medicine and healthcare1486Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: legal and government1487Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: business and finance1460Not measuredOnly Gemini 3.1 Pro Preview measured
FACTS Benchmark Suite69.1%Not measuredOnly Gemini 3.1 Pro Preview measured
Neither model has a result on the other 5 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index03
Web design benchmarks for Gemini 3.1 Pro Preview and Inkling 2 Mini
BenchmarkGemini 3.1 Pro PreviewInkling 2 MiniLeader
Design Arena: websites1221Not measuredOnly Gemini 3.1 Pro Preview measured
Design Arena: UI components12091292Inkling 2 Mini
Design Arena: game dev11741287Inkling 2 Mini
Design Arena: data viz1203Not measuredOnly Gemini 3.1 Pro Preview measured
Design Arena: 3D12011308Inkling 2 Mini
Design Arena: all code categories1212Not measuredOnly Gemini 3.1 Pro Preview measured
Design Arena: SVG1269Not measuredOnly Gemini 3.1 Pro Preview measured
Design Arena: ASCII art1255Not measuredOnly Gemini 3.1 Pro Preview measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index03
General benchmarks for Gemini 3.1 Pro Preview and Inkling 2 Mini
BenchmarkGemini 3.1 Pro PreviewInkling 2 MiniLeader
Vals IndexNot measured46.5%Only Inkling 2 Mini measured
Public Benefits Bench (Vals AI)53.8%Not measuredOnly Gemini 3.1 Pro Preview measured
SAGE (Vals AI)83.2%85.9%Inkling 2 Mini
MedScribe (Vals AI)76.1%86.4%Inkling 2 Mini
Vals Multimodal Index56.1%Not measuredOnly Gemini 3.1 Pro Preview measured
IFBench77.1%Not measuredOnly Gemini 3.1 Pro Preview measured
Long context reasoning (AA-LCR)82.0%Not measuredOnly Gemini 3.1 Pro Preview measured
GDPval-AA7991319Inkling 2 Mini
DTBench97.1%Not measuredOnly Gemini 3.1 Pro Preview measured
LMCA53.8%Not measuredOnly Gemini 3.1 Pro Preview measured
CL-bench20.8%Not measuredOnly Gemini 3.1 Pro Preview measured
Furniture assembly26.7%Not measuredOnly Gemini 3.1 Pro Preview measured
ExploitBench26.1%Not measuredOnly Gemini 3.1 Pro Preview measured
CL-bench Life16.9%Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text1480Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: instruction following1465Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: creative writing1483Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Vision1296Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: English1478Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: non-English1476Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: Chinese1529Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: German1491Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: Japanese1495Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: Korean1457Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: French1487Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: Spanish1480Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: Russian1497Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: Polish1498Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: multi-turn1486Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: longer queries1482Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: writing and language1481Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Text: entertainment and media1465Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Vision: English1286Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Vision: Chinese1362Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Vision: reading text1305Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Vision: humor1324Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Vision: captioning1343Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Vision: recognizing things1327Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Vision: creative writing1324Not measuredOnly Gemini 3.1 Pro Preview measured
LMArena Document1443Not measuredOnly Gemini 3.1 Pro Preview measured
EQ-Bench 41132Not measuredOnly Gemini 3.1 Pro Preview measured
Neither model has a result on the other 8 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemini 3.1 Pro Preview and Inkling 2 Mini
BenchmarkGemini 3.1 Pro PreviewInkling 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 3.1 Pro Preview$0.0080Fits in one request
Inkling 2 Mini$0.0002Fits in one request

Inkling 2 Mini costs less

Repository review

50K input + 3K output tokens

Gemini 3.1 Pro Preview$0.136Fits in one request
Inkling 2 Mini$0.0049Fits in one request

Inkling 2 Mini costs less

Agent loop

200K input + 10K output tokens

Gemini 3.1 Pro Preview$0.520Fits 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 3.1 Pro Preview and Inkling 2 Mini
SpecificationGoogle Gemini 3.1 Pro PreviewThinking Machines Inkling 2 Mini
MakerGoogleThinking Machines
WeightsNo public weights listedOpen weights
ReleasedFebruary 19, 2026November 21, 2026
Context window1.05M1.05M
Input $/Mtok$2.00$0.0775
Output $/Mtok$12.00$0.325
Coding index32.339.5
Independent measurements behind it42
Cost per solved task$0.99Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 3.1 Pro Preview better than Inkling 2 Mini for coding?

Pick Inkling 2 Mini for coding: it scores 39.5 on the Vibe Coding Index against 32.3 for Gemini 3.1 Pro Preview, though on 2 benchmarks against 4. Pick Gemini 3.1 Pro Preview for work measured by IOI (Vals AI) or Legal Research Bench (Vals AI), where it leads.

Which is cheaper, Gemini 3.1 Pro Preview or Inkling 2 Mini?

Gemini 3.1 Pro Preview costs $2.00 per million input tokens and $12.00 per million output tokens; Inkling 2 Mini costs $0.0775 and $0.325. Cost per solved task is known for Gemini 3.1 Pro Preview only.

Which has the bigger context window, Gemini 3.1 Pro Preview or Inkling 2 Mini?

Neither: both take 1.05M tokens.

How many benchmarks is the Gemini 3.1 Pro Preview vs Inkling 2 Mini comparison based on?

20 benchmarks have a result for both models as of November 22, 2026. Gemini 3.1 Pro Preview's coding index rests on 4 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-3-1-pro-preview-vs-thinkingmachines-inkling-2-mini" title="Gemini 3.1 Pro Preview 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-3-1-pro-preview-vs-thinkingmachines-inkling-2-mini">LLMBenchmark.ai, Gemini 3.1 Pro Preview vs Inkling 2 Mini</a></p>