Enter opens the highlighted result. Esc closes.

Gemini 3.8 Flash vs Inkling 2 Mini

Gemini 3.8 Flash leads Inkling 2 Mini on coding, 60.3 to 39.5 on the Vibe Coding Index, and Inkling 2 Mini costs 11.5x less per output token ($0.325 vs $3.75 per million). Updated November 22, 2026; 29 benchmarks have a result for both.

Gemini 3.8 FlashGoogle
Coding
60.3
Overall
64.4
Output $/M
$3.75
25
T Inkling 2 MiniThinking Machines
Coding
39.5
Overall
No data
Output $/M
$0.325
4
vs boards won of 29 shared

Gemini 3.8 Flash or Inkling 2 Mini: which to pick

Pick Gemini 3.8 Flash for coding: it scores 60.3 on the Vibe Coding Index against 39.5 for Inkling 2 Mini.

Pick Inkling 2 Mini for output tokens 11.5x cheaper ($0.325 vs $3.75 per million) and work measured by CyberBench (Vals AI) or Design Arena: game dev, where it leads.

Shared results
29
Gemini 3.8 Flash only
118
Inkling 2 Mini only
0
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 3.8 Flash 60.3 from 6 benchmarks, Inkling 2 Mini 39.5 from 2 benchmarks.
Widest category
Reasoning, 20.3 points apart on average over 3 shared benchmarks.
Widest single gap
IOI (Vals AI): Gemini 3.8 Flash 56.9% against Inkling 2 Mini 11.6%, 45.3 points apart on a 0 to 100 scale.
Output price
Gemini 3.8 Flash $3.75 against Inkling 2 Mini $0.325 per million output tokens, 11.5x 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 3.8 FlashBarsInkling 2 MiniTies
Coding81
Intelligence10
Agentic work70
Reasoning30
Knowledge20
Web design12
General31
All shared boards254
CodingLike-for-likeSix of these boards feed the Vibe Coding Index81
Coding benchmarks for Gemini 3.8 Flash and Inkling 2 Mini
BenchmarkGemini 3.8 FlashInkling 2 MiniLeader
LiveBench coding73.3%Not measuredOnly Gemini 3.8 Flash measured
LMArena WebDev1584Not measuredOnly Gemini 3.8 Flash measured
LiveCodeBench (Vals AI)89.5%Not measuredOnly Gemini 3.8 Flash measured
SWE-bench Verified (Vals AI)80.0%Not measuredOnly Gemini 3.8 Flash measured
Terminal-Bench 4 (Vals AI)19.7%6.6%Gemini 3.8 Flash
Vibe Code Bench (Vals AI)78.7%77.9%Gemini 3.8 Flash
Code migration (Vals AI)36.5%Not measuredOnly Gemini 3.8 Flash measured
ProgramBench (Vals AI)1.0%0.5%Gemini 3.8 Flash
IOI (Vals AI)56.9%11.6%Gemini 3.8 Flash
Terminal-Bench 2.1 (Vals AI)81.3%Not measuredOnly Gemini 3.8 Flash measured
SWE-bench Multimodal (Vals AI)40.8%37.9%Gemini 3.8 Flash
Vibe Code Bench 1-100 (Vals AI)18.8%Not measuredOnly Gemini 3.8 Flash measured
SkillsBench (Vals AI)58.0%43.2%Gemini 3.8 Flash
CyberBench (Vals AI)43.8%74.6%Inkling 2 Mini
SciCode56.6%Not measuredOnly Gemini 3.8 Flash measured
Terminal-Bench 4.0 (Artificial Analysis run)19.7%5.6%Gemini 3.8 Flash
FrontierCode 2.018.7%15.1%Gemini 3.8 Flash
FrontierCode41.2%Not measuredOnly Gemini 3.8 Flash measured
FrontierSWE19.6%Not measuredOnly Gemini 3.8 Flash measured
WeirdML84.8%Not measuredOnly Gemini 3.8 Flash measured
MirrorCode38.9%Not measuredOnly Gemini 3.8 Flash measured
ALE-Bench1269.7Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: coding1509Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: software and IT1509Not measuredOnly Gemini 3.8 Flash measured
LMArena WebDev: React1575Not measuredOnly Gemini 3.8 Flash measured
LMArena WebDev: HTML1610Not measuredOnly Gemini 3.8 Flash measured
LMArena WebDev: from an image1592Not measuredOnly Gemini 3.8 Flash measured
SciCode12.3%Not measuredOnly Gemini 3.8 Flash measured
SWE-Bench Pro V294.9%Not measuredOnly Gemini 3.8 Flash measured
SWE Atlas: Codebase QnA47.0%Not measuredOnly Gemini 3.8 Flash measured
SWE Atlas: Refactoring44.8%Not measuredOnly Gemini 3.8 Flash measured
SWE Atlas: Test Writing53.7%Not measuredOnly Gemini 3.8 Flash measured
GameBench 264.0Not measuredOnly Gemini 3.8 Flash measured
Terminal-Bench 4.019.1%Not measuredOnly Gemini 3.8 Flash measured
Neither model has a result on the other 18 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Gemini 3.8 Flash and Inkling 2 Mini
BenchmarkGemini 3.8 FlashInkling 2 MiniLeader
AA Intelligence Index30.820.1Gemini 3.8 Flash
Epoch Capabilities Index158.8Not measuredOnly Gemini 3.8 Flash measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index70
Agentic work benchmarks for Gemini 3.8 Flash and Inkling 2 Mini
BenchmarkGemini 3.8 FlashInkling 2 MiniLeader
Design Arena: agents building web apps1204Not measuredOnly Gemini 3.8 Flash measured
Design Arena: agents building full-stack apps1218Not measuredOnly Gemini 3.8 Flash measured
Design Arena: agents building mobile apps1225Not measuredOnly Gemini 3.8 Flash measured
Design Arena: agents building Android apps1091Not measuredOnly Gemini 3.8 Flash measured
Design Arena: agents building Godot games1239Not measuredOnly Gemini 3.8 Flash measured
Design Arena: PowerPoint slides1148Not measuredOnly Gemini 3.8 Flash measured
Design Arena: spreadsheets1025Not measuredOnly Gemini 3.8 Flash measured
LiveBench research79.4%Not measuredOnly Gemini 3.8 Flash measured
LiveBench browser45.1%Not measuredOnly Gemini 3.8 Flash measured
LiveBench long agentic16.5%Not measuredOnly Gemini 3.8 Flash measured
SREBench (Vals AI)11.1%0.0%Gemini 3.8 Flash
Finance Agent (Vals AI)61.4%Not measuredOnly Gemini 3.8 Flash measured
Tax Agent Bench (Vals AI)32.1%14.1%Gemini 3.8 Flash
Legal Research Bench (Vals AI)38.9%17.8%Gemini 3.8 Flash
Harvey's Legal Agent Benchmark (Vals AI)12.1%5.0%Gemini 3.8 Flash
Excel Modeling Benchmark (Vals AI)72.2%Not measuredOnly Gemini 3.8 Flash measured
BioMysteryBench (Vals AI)62.2%47.8%Gemini 3.8 Flash
Terminal-Bench-Science (Vals AI)8.6%0.0%Gemini 3.8 Flash
Vals Science Index35.8%23.6%Gemini 3.8 Flash
Time Horizon Index (Vals AI)18.8%Not measuredOnly Gemini 3.8 Flash measured
CUA-bench (Vals AI)4.2%Not measuredOnly Gemini 3.8 Flash measured
APEX-Agents64.3%Not measuredOnly Gemini 3.8 Flash measured
Remote Labor Index5.8%Not measuredOnly Gemini 3.8 Flash measured
Vending-Bench 2$5,094Not measuredOnly Gemini 3.8 Flash 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 3.8 Flash and Inkling 2 Mini
BenchmarkGemini 3.8 FlashInkling 2 MiniLeader
GPQA Diamond94.4%Not measuredOnly Gemini 3.8 Flash measured
LiveBench reasoning89.3%Not measuredOnly Gemini 3.8 Flash measured
MysteryMechanism (Vals AI)36.5%23.0%Gemini 3.8 Flash
MMMU Pro (Vals AI)89.1%Not measuredOnly Gemini 3.8 Flash measured
GPQA Diamond (Artificial Analysis run)95.3%Not measuredOnly Gemini 3.8 Flash measured
Humanity's Last Exam (Artificial Analysis run)47.8%Not measuredOnly Gemini 3.8 Flash measured
HLE-Diamond (Artificial Analysis run)33.1%15.2%Gemini 3.8 Flash
CritPt v2, hard subset (Artificial Analysis run)46.5%17.0%Gemini 3.8 Flash
GPQA Diamond (Epoch AI run)95.4%Not measuredOnly Gemini 3.8 Flash measured
ARC-AGI98.5%Not measuredOnly Gemini 3.8 Flash measured
ARC-AGI-289.2%Not measuredOnly Gemini 3.8 Flash measured
SimpleBench82.4%Not measuredOnly Gemini 3.8 Flash measured
Chess puzzles58.0%Not measuredOnly Gemini 3.8 Flash measured
Mystery game puzzles47.0%Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: hard prompts1509Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: expert1526Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: hard prompts in English1505Not measuredOnly Gemini 3.8 Flash measured
LMArena Vision: diagrams1347Not measuredOnly Gemini 3.8 Flash measured
LMArena Vision: homework1352Not measuredOnly Gemini 3.8 Flash measured
Humanity's Last Exam (Scale run)34.3%Not measuredOnly Gemini 3.8 Flash measured
GoBench1614Not measuredOnly Gemini 3.8 Flash measured
Neither model has a result on the other 5 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Math benchmarks for Gemini 3.8 Flash and Inkling 2 Mini
BenchmarkGemini 3.8 FlashInkling 2 MiniLeader
OTIS Mock AIME98.9%Not measuredOnly Gemini 3.8 Flash measured
FrontierMath, tiers 1 to 368.4%Not measuredOnly Gemini 3.8 Flash measured
FrontierMath, tier 422.0%Not measuredOnly Gemini 3.8 Flash measured
ProofBench48.0%Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: math1525Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: mathematical work1519Not measuredOnly Gemini 3.8 Flash measured
MathArena30.8%Not measuredOnly Gemini 3.8 Flash 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 3.8 Flash and Inkling 2 Mini
BenchmarkGemini 3.8 FlashInkling 2 MiniLeader
MMLU Pro90.2%Not measuredOnly Gemini 3.8 Flash measured
LegalBench (Vals AI)87.0%Not measuredOnly Gemini 3.8 Flash measured
TaxEval (Vals AI)74.5%Not measuredOnly Gemini 3.8 Flash measured
MortgageTax (Vals AI)65.3%Not measuredOnly Gemini 3.8 Flash measured
MedCode (Vals AI)48.1%25.7%Gemini 3.8 Flash
AA-Omniscience23.7-8.6Gemini 3.8 Flash
SimpleQA Verified69.7%Not measuredOnly Gemini 3.8 Flash measured
GeoBench86.0%Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: science1521Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: medicine and healthcare1505Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: legal and government1503Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: business and finance1484Not measuredOnly Gemini 3.8 Flash measured
FACTS Benchmark Suite71.2%Not measuredOnly Gemini 3.8 Flash measured
PRBench Finance49.5%Not measuredOnly Gemini 3.8 Flash measured
PRBench Legal49.5%Not measuredOnly Gemini 3.8 Flash measured
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index12
Web design benchmarks for Gemini 3.8 Flash and Inkling 2 Mini
BenchmarkGemini 3.8 FlashInkling 2 MiniLeader
Design Arena: websites1287Not measuredOnly Gemini 3.8 Flash measured
Design Arena: UI components12981292Gemini 3.8 Flash
Design Arena: game dev12791287Inkling 2 Mini
Design Arena: data viz1272Not measuredOnly Gemini 3.8 Flash measured
Design Arena: 3D12621308Inkling 2 Mini
Design Arena: all code categories1285Not measuredOnly Gemini 3.8 Flash measured
Design Arena: SVG1283Not measuredOnly Gemini 3.8 Flash measured
Design Arena: ASCII art1258Not measuredOnly Gemini 3.8 Flash measured
LiveBench design69.7%Not measuredOnly Gemini 3.8 Flash measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index31
General benchmarks for Gemini 3.8 Flash and Inkling 2 Mini
BenchmarkGemini 3.8 FlashInkling 2 MiniLeader
Vals Index56.0%46.5%Gemini 3.8 Flash
LiveBench data analysis54.0%Not measuredOnly Gemini 3.8 Flash measured
Public Benefits Bench (Vals AI)65.3%Not measuredOnly Gemini 3.8 Flash measured
SAGE (Vals AI)88.2%85.9%Gemini 3.8 Flash
MedScribe (Vals AI)84.5%86.4%Inkling 2 Mini
Long context reasoning (AA-LCR)84.0%Not measuredOnly Gemini 3.8 Flash measured
GDPval-AA14421319Gemini 3.8 Flash
DTBench95.7%Not measuredOnly Gemini 3.8 Flash measured
LMCA52.9%Not measuredOnly Gemini 3.8 Flash measured
Surface Evolver Bench76.9%Not measuredOnly Gemini 3.8 Flash measured
Furniture assembly31.7%Not measuredOnly Gemini 3.8 Flash measured
LMArena Text1500Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: instruction following1494Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: creative writing1494Not measuredOnly Gemini 3.8 Flash measured
LMArena Vision1316Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: English1499Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: non-English1493Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: Chinese1562Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: German1506Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: Japanese1522Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: Korean1474Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: French1499Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: Spanish1485Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: Russian1516Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: Polish1510Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: multi-turn1502Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: longer queries1508Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: writing and language1496Not measuredOnly Gemini 3.8 Flash measured
LMArena Text: entertainment and media1482Not measuredOnly Gemini 3.8 Flash measured
LMArena Vision: English1318Not measuredOnly Gemini 3.8 Flash measured
LMArena Vision: Chinese1391Not measuredOnly Gemini 3.8 Flash measured
LMArena Vision: reading text1331Not measuredOnly Gemini 3.8 Flash measured
LMArena Vision: humor1310Not measuredOnly Gemini 3.8 Flash measured
LMArena Vision: creative writing1314Not measuredOnly Gemini 3.8 Flash measured
LMArena Document1482Not measuredOnly Gemini 3.8 Flash measured
Neither model has a result on the other 14 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemini 3.8 Flash and Inkling 2 Mini
BenchmarkGemini 3.8 FlashInkling 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 3.8 Flash$0.0026Fits in one request
Inkling 2 Mini$0.0002Fits in one request

Inkling 2 Mini costs less

Repository review

50K input + 3K output tokens

Gemini 3.8 Flash$0.049Fits in one request
Inkling 2 Mini$0.0049Fits in one request

Inkling 2 Mini costs less

Agent loop

200K input + 10K output tokens

Gemini 3.8 Flash$0.188Fits 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 3.8 Flash and Inkling 2 Mini
SpecificationGoogle Gemini 3.8 FlashThinking Machines Inkling 2 Mini
MakerGoogleThinking Machines
WeightsNo public weights listedOpen weights
ReleasedSeptember 2, 2026November 21, 2026
Context window1.05M1.05M
Input $/Mtok$0.75$0.0775
Output $/Mtok$3.75$0.325
Coding index60.339.5
Independent measurements behind it62
Cost per solved task$2.74Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 3.8 Flash better than Inkling 2 Mini for coding?

Pick Gemini 3.8 Flash for coding: it scores 60.3 on the Vibe Coding Index against 39.5 for Inkling 2 Mini. Pick Inkling 2 Mini for output tokens 11.5x cheaper ($0.325 vs $3.75 per million) and work measured by CyberBench (Vals AI) or Design Arena: game dev, where it leads.

Which is cheaper, Gemini 3.8 Flash or Inkling 2 Mini?

Gemini 3.8 Flash costs $0.75 per million input tokens and $3.75 per million output tokens; Inkling 2 Mini costs $0.0775 and $0.325. Cost per solved task is known for Gemini 3.8 Flash only.

Which has the bigger context window, Gemini 3.8 Flash or Inkling 2 Mini?

Neither: both take 1.05M tokens.

How many benchmarks is the Gemini 3.8 Flash vs Inkling 2 Mini comparison based on?

29 benchmarks have a result for both models as of November 22, 2026. Gemini 3.8 Flash's coding index rests on 6 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-3-8-flash-vs-thinkingmachines-inkling-2-mini" title="Gemini 3.8 Flash 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-3-8-flash-vs-thinkingmachines-inkling-2-mini">LLMBenchmark.ai, Gemini 3.8 Flash vs Inkling 2 Mini</a></p>