Enter opens the highlighted result. Esc closes.

Gemma 4 31B vs Inkling

Gemma 4 31B leads Inkling on coding, 39.0 to 31.5 on the Vibe Coding Index, and Gemma 4 31B costs 10.1x less per output token ($0.40 vs $4.05 per million). Updated October 21, 2026; 52 benchmarks have a result for both.

Replace Gemma 4 31B Replace Inkling
Gemma 4 31BGoogle
Coding
39.0
Overall
42.1
Output $/M
$0.40
17
T InklingThinking Machines
Coding
31.5
Overall
46.5
Output $/M
$4.05
35
vs boards won of 52 shared

Gemma 4 31B or Inkling: which to pick

Pick Gemma 4 31B for coding: it scores 39.0 on the Vibe Coding Index against 31.5 for Inkling, though on 2 benchmarks against 6.

Pick Inkling for a larger context window (524K against 262K tokens) and work measured by LiveBench coding or LMArena WebDev, where it leads.

Model AGemma 4 31BGoogle39.0/1002 independent benchmarksNo cost per solved taskModel BInklingThinking Machines31.5/1006 independent benchmarks$0.76 per solved task
Shared results
52
Gemma 4 31B only
19
Inkling only
50
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
Gemma 4 31B 39.0 from 2 benchmarks, Inkling 31.5 from 6 benchmarks.
Widest category
Agentic work, 11.6 points apart on average over 4 shared benchmarks.
Widest single gap
SimpleQA Verified: Gemma 4 31B 10.4% against Inkling 40.3%, 29.9 points apart on a 0 to 100 scale.
Output price
Gemma 4 31B $0.40 against Inkling $4.05 per million output tokens, 10.1x apart.
Context window
Gemma 4 31B takes 262K tokens, Inkling 524K.

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
CategoryGemma 4 31BBarsInklingTies
Coding19
Intelligence02
Agentic work04
Reasoning16
Math12
Knowledge24
Web design10
General118
All shared boards1735
CodingLike-for-likeSix of these boards feed the Vibe Coding Index19
Coding benchmarks for Gemma 4 31B and Inkling
BenchmarkGemma 4 31BInklingLeader
LiveBench coding49.0%64.0%Inkling
LMArena WebDev13671414Inkling
AA Coding Index43.452.1Inkling
LiveCodeBench (Vals AI)Not measured85.5%Only Inkling measured
SWE-bench Verified (Vals AI)Not measured77.6%Only Inkling measured
Terminal-Bench 4 (Vals AI)Not measured0.5%Only Inkling measured
Vibe Code Bench (Vals AI)Not measured19.2%Only Inkling measured
Code migration (Vals AI)Not measured11.8%Only Inkling measured
ProgramBench (Vals AI)Not measured0.0%Only Inkling measured
IOI (Vals AI)Not measured14.9%Only Inkling measured
Terminal-Bench 2.1 (Vals AI)Not measured47.6%Only Inkling measured
Vibe Code Bench 1-100 (Vals AI)Not measured7.3%Only Inkling measured
SkillsBench (Vals AI)Not measured26.1%Only Inkling measured
CyberBench (Vals AI)Not measured66.8%Only Inkling measured
SciCode45.5%47.0%Inkling
Terminal-Bench Hard (Artificial Analysis run)36.4%Not measuredOnly Gemma 4 31B measured
FrontierCodeNot measured14.0%Only Inkling measured
FrontierSWENot measured4.1%Only Inkling measured
WeirdML52.3%32.3%Gemma 4 31B
ALE-Bench925.5946.0Inkling
LMArena Text: coding14591466Inkling
LMArena Text: software and IT14631465Inkling
LMArena WebDev: React13591404Inkling
LMArena WebDev: HTML13801399Inkling
SciCode8.9%Not measuredOnly Gemma 4 31B measured
Neither model has a result on the other 14 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Gemma 4 31B and Inkling
BenchmarkGemma 4 31BInklingLeader
AA Intelligence Index14.725.0Inkling
Epoch Capabilities Index143.0148.4Inkling
Agentic workLike-for-likePublic boards, shown as published, kept out of the index04
Agentic work benchmarks for Gemma 4 31B and Inkling
BenchmarkGemma 4 31BInklingLeader
AA Agentic Index4.222.5Inkling
Design Arena: agents building web appsNot measured1196Only Inkling measured
LiveBench research44.4%59.9%Inkling
LiveBench browser4.0%16.0%Inkling
LiveBench long agentic13.3%14.1%Inkling
SREBench (Vals AI)Not measured0.0%Only Inkling measured
Finance Agent (Vals AI)Not measured46.6%Only Inkling measured
Tax Agent Bench (Vals AI)Not measured15.3%Only Inkling measured
Legal Research Bench (Vals AI)Not measured28.4%Only Inkling measured
Harvey's Legal Agent Benchmark (Vals AI)Not measured3.8%Only Inkling measured
Excel Modeling Benchmark (Vals AI)Not measured38.4%Only Inkling measured
τ²-Bench Telecom65.5%Not measuredOnly Gemma 4 31B measured
APEX-AgentsNot measured33.8%Only Inkling measured
Neither model has a result on the other 28 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index16
Reasoning benchmarks for Gemma 4 31B and Inkling
BenchmarkGemma 4 31BInklingLeader
GPQA DiamondNot measured87.1%Only Inkling measured
LiveBench reasoning68.3%78.3%Inkling
MMMU Pro (Vals AI)Not measured78.5%Only Inkling measured
GPQA Diamond (Artificial Analysis run)85.7%87.2%Inkling
Humanity's Last Exam (Artificial Analysis run)23.6%31.9%Inkling
GPQA Diamond (Epoch AI run)75.8%88.3%Inkling
ARC-AGINot measured79.5%Only Inkling measured
ARC-AGI-2Not measured36.5%Only Inkling measured
SimpleBenchNot measured50.0%Only Inkling measured
Chess puzzlesNot measured21.0%Only Inkling measured
LMArena Text: hard prompts14481451Inkling
LMArena Text: expert14641466Inkling
LMArena Text: hard prompts in English14561448Gemma 4 31B
LMArena Vision: diagrams1283Not measuredOnly Gemma 4 31B measured
LMArena Vision: homework1310Not measuredOnly Gemma 4 31B measured
Kagi LLM Benchmark63.5%Not measuredOnly Gemma 4 31B measured
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index12
Math benchmarks for Gemma 4 31B and Inkling
BenchmarkGemma 4 31BInklingLeader
OTIS Mock AIME73.3%88.9%Inkling
FrontierMath, tiers 1 to 3Not measured33.3%Only Inkling measured
FrontierMath, tier 4Not measured4.9%Only Inkling measured
ProofBenchNot measured0.0%Only Inkling measured
LMArena Text: math14631479Inkling
LMArena Text: mathematical work14651460Gemma 4 31B
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index24
Knowledge benchmarks for Gemma 4 31B and Inkling
BenchmarkGemma 4 31BInklingLeader
MMLU ProNot measured86.3%Only Inkling measured
LegalBench (Vals AI)Not measured83.0%Only Inkling measured
CaseLaw (Vals AI)52.6%Not measuredOnly Gemma 4 31B measured
CorpFin (Vals AI)Not measured68.6%Only Inkling measured
TaxEval (Vals AI)Not measured75.3%Only Inkling measured
MortgageTax (Vals AI)61.4%64.0%Inkling
MedCode (Vals AI)Not measured41.2%Only Inkling measured
SimpleQA Verified10.4%40.3%Inkling
LMArena Text: science14571455Gemma 4 31B
LMArena Text: medicine and healthcare14511447Gemma 4 31B
LMArena Text: legal and government14381448Inkling
LMArena Text: business and finance14301438Inkling
FACTS Benchmark Suite45.3%Not measuredOnly Gemma 4 31B measured
Neither model has a result on the other 5 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index10
Web design benchmarks for Gemma 4 31B and Inkling
BenchmarkGemma 4 31BInklingLeader
Design Arena: websitesNot measured1224Only Inkling measured
Design Arena: UI componentsNot measured1201Only Inkling measured
Design Arena: game devNot measured1166Only Inkling measured
Design Arena: data vizNot measured1159Only Inkling measured
Design Arena: 3DNot measured1161Only Inkling measured
Design Arena: all code categoriesNot measured1206Only Inkling measured
Design Arena: SVGNot measured1110Only Inkling measured
Design Arena: ASCII artNot measured1089Only Inkling measured
LiveBench design58.4%58.3%Gemma 4 31B
GeneralLike-for-likePublic boards, shown as published, kept out of the index118
General benchmarks for Gemma 4 31B and Inkling
BenchmarkGemma 4 31BInklingLeader
Vals IndexNot measured29.0%Only Inkling measured
LiveBench data analysis53.3%72.8%Inkling
Public Benefits Bench (Vals AI)Not measured58.5%Only Inkling measured
SAGE (Vals AI)55.0%36.5%Gemma 4 31B
MedScribe (Vals AI)Not measured85.4%Only Inkling measured
Vals Multimodal IndexNot measured49.4%Only Inkling measured
IFBench75.6%Not measuredOnly Gemma 4 31B measured
Long context reasoning (AA-LCR)69.7%77.3%Inkling
DTBench82.7%87.5%Inkling
LMCA39.3%37.6%Gemma 4 31B
Surface Evolver Bench30.6%Not measuredOnly Gemma 4 31B measured
LMArena Text14431442Gemma 4 31B
LMArena Text: instruction following14331425Gemma 4 31B
LMArena Text: creative writing14171390Gemma 4 31B
LMArena Vision1276Not measuredOnly Gemma 4 31B measured
LMArena Text: English14511442Gemma 4 31B
LMArena Text: non-English14301434Inkling
LMArena Text: Chinese14751493Inkling
LMArena Text: GermanNot measured1445Only Inkling measured
LMArena Text: JapaneseNot measured1429Only Inkling measured
LMArena Text: KoreanNot measured1403Only Inkling measured
LMArena Text: French14361455Inkling
LMArena Text: Spanish14421449Inkling
LMArena Text: Russian14601430Gemma 4 31B
LMArena Text: Polish14331450Inkling
LMArena Text: multi-turn14521437Gemma 4 31B
LMArena Text: longer queries14461435Gemma 4 31B
LMArena Text: writing and language14321404Gemma 4 31B
LMArena Text: entertainment and media14051394Gemma 4 31B
LMArena Vision: English1271Not measuredOnly Gemma 4 31B measured
LMArena Vision: Chinese1326Not measuredOnly Gemma 4 31B measured
LMArena Vision: reading text1282Not measuredOnly Gemma 4 31B measured
LMArena Vision: humor1280Not measuredOnly Gemma 4 31B measured
LMArena Vision: captioning1218Not measuredOnly Gemma 4 31B measured
LMArena Vision: recognizing things1226Not measuredOnly Gemma 4 31B measured
LMArena Vision: creative writing1285Not measuredOnly Gemma 4 31B measured
LMArena Document1425Not measuredOnly Gemma 4 31B measured
Neither model has a result on the other 9 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemma 4 31B and Inkling
BenchmarkGemma 4 31BInklingLeader
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

Gemma 4 31B$0.0003Fits in one request
Inkling$0.0030Fits in one request

Gemma 4 31B costs less

Repository review

50K input + 3K output tokens

Gemma 4 31B$0.0082Fits in one request
Inkling$0.061Fits in one request

Gemma 4 31B costs less

Agent loop

200K input + 10K output tokens

Gemma 4 31B$0.032Fits in one request
Inkling$0.235Fits in one request

Gemma 4 31B 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 Gemma 4 31B and Inkling
SpecificationGoogle Gemma 4 31BThinking Machines Inkling
MakerGoogleThinking Machines
WeightsOpen weightsOpen weights
ReleasedApril 2, 2026July 17, 2026
Context window262K524K
Input $/Mtok$0.14$0.975
Output $/Mtok$0.40$4.05
Coding index39.031.5
Independent measurements behind it26
Cost per solved taskNot computable$0.76
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 4 31B better than Inkling for coding?

Pick Gemma 4 31B for coding: it scores 39.0 on the Vibe Coding Index against 31.5 for Inkling, though on 2 benchmarks against 6. Pick Inkling for a larger context window (524K against 262K tokens) and work measured by LiveBench coding or LMArena WebDev, where it leads.

Which is cheaper, Gemma 4 31B or Inkling?

Gemma 4 31B costs $0.14 per million input tokens and $0.40 per million output tokens; Inkling costs $0.975 and $4.05. Cost per solved task is known for Inkling only.

Which has the bigger context window, Gemma 4 31B or Inkling?

Inkling, with 524K tokens against 262K.

How many benchmarks is the Gemma 4 31B vs Inkling comparison based on?

52 benchmarks have a result for both models as of October 21, 2026. Gemma 4 31B's coding index rests on 2 independent benchmarks and Inkling'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/gemma-4-31b-it-vs-thinkingmachines-inkling" title="Gemma 4 31B vs Inkling, 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/gemma-4-31b-it-vs-thinkingmachines-inkling">LLMBenchmark.ai, Gemma 4 31B vs Inkling</a></p>