Enter opens the highlighted result. Esc closes.

Gemma 4 31B vs GPT-6.1 Sol

Updated October 21, 2026. 52 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Gemma 4 31B Replace GPT-6.1 Sol
Gemma 4 31BGoogle
Coding
38.3
Overall
14.7
Output $/M
$0.40
7
GPT-6.1 SolOpenAI
Coding
88.7
Overall
51.8
Output $/M
$10.00
45
vs boards won of 52 shared

Decision reading

Pick GPT-6.1 Sol for coding: it scores 88.7 on the Vibe Coding Index against 38.3 for Gemma 4 31B.

Pick Gemma 4 31B when output tokens cost 25.0x less, or when what matters is LMArena Text: science or LMArena Text: medicine and healthcare, where it leads.

Model AGemma 4 31BGoogle38.3/1002 independent benchmarksNo cost per solved taskModel BGPT-6.1 SolOpenAI88.7/1002 independent benchmarksNo cost per solved task
Shared results
52
Gemma 4 31B only
16
GPT-6.1 Sol only
43
Like-for-like categories
8 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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 38.3 from 2 benchmarks, GPT-6.1 Sol 88.7 from 2 benchmarks.
Widest category
Agentic work, 60.9 points apart on average over 3 shared benchmarks.
Widest single gap
LiveBench browser: Gemma 4 31B 4.0% against GPT-6.1 Sol 88.0%, 84.0 points apart on a 0 to 100 scale.
Output price
Gemma 4 31B $0.40 against GPT-6.1 Sol $10.00 per million output tokens, 25.0x apart.
Context window
Gemma 4 31B takes 262K tokens, GPT-6.1 Sol 1.05M.

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 31BBarsGPT-6.1 SolTies
Coding08
Intelligence02
Agentic work03
Reasoning08
Math03
Knowledge23
Web design01
General517
All shared boards745
CodingLike-for-likeFour of these boards feed the Vibe Coding Index08
Coding benchmarks for Gemma 4 31B and GPT-6.1 Sol
BenchmarkGemma 4 31BGPT-6.1 SolLeader
LiveBench coding49.0%96.0%GPT-6.1 Sol
LMArena WebDev13671753GPT-6.1 Sol
AA Coding Index43.4Not measuredOnly Gemma 4 31B measured
Terminal-Bench 4 (Vals AI)Not measured55.0%Only GPT-6.1 Sol measured
Vibe Code Bench (Vals AI)Not measured88.9%Only GPT-6.1 Sol measured
Code migration (Vals AI)Not measured65.1%Only GPT-6.1 Sol measured
ProgramBench (Vals AI)Not measured3.0%Only GPT-6.1 Sol measured
IOI (Vals AI)Not measured96.9%Only GPT-6.1 Sol measured
SWE-bench Multimodal (Vals AI)Not measured43.5%Only GPT-6.1 Sol measured
CyberBench (Vals AI)Not measured39.3%Only GPT-6.1 Sol measured
SciCode45.5%55.8%GPT-6.1 Sol
Terminal-Bench Hard (Artificial Analysis run)36.4%Not measuredOnly Gemma 4 31B measured
FrontierCodeNot measured50.2%Only GPT-6.1 Sol measured
WeirdML52.3%Not measuredOnly Gemma 4 31B measured
ALE-Bench925.52743.8GPT-6.1 Sol
LMArena Text: coding14591478GPT-6.1 Sol
LMArena Text: software and IT14631476GPT-6.1 Sol
LMArena WebDev: React13591754GPT-6.1 Sol
LMArena WebDev: HTML13801800GPT-6.1 Sol
LMArena WebDev: from an imageNot measured1702Only GPT-6.1 Sol measured
Neither model has a result on the other 18 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Gemma 4 31B and GPT-6.1 Sol
BenchmarkGemma 4 31BGPT-6.1 SolLeader
AA Intelligence Index14.751.8GPT-6.1 Sol
Epoch Capabilities Index143.0168.4GPT-6.1 Sol
Agentic workLike-for-likePublic boards, shown as published, kept out of the index03
Agentic work benchmarks for Gemma 4 31B and GPT-6.1 Sol
BenchmarkGemma 4 31BGPT-6.1 SolLeader
AA Agentic Index4.2Not measuredOnly Gemma 4 31B measured
Design Arena: agents building mobile appsNot measured1190Only GPT-6.1 Sol measured
Design Arena: spreadsheetsNot measured1250Only GPT-6.1 Sol measured
LiveBench research44.4%83.5%GPT-6.1 Sol
LiveBench browser4.0%88.0%GPT-6.1 Sol
LiveBench long agentic13.3%73.0%GPT-6.1 Sol
SREBench (Vals AI)Not measured50.8%Only GPT-6.1 Sol measured
Finance Agent (Vals AI)Not measured52.0%Only GPT-6.1 Sol measured
Tax Agent Bench (Vals AI)Not measured21.8%Only GPT-6.1 Sol measured
Legal Research Bench (Vals AI)Not measured38.5%Only GPT-6.1 Sol measured
Harvey's Legal Agent Benchmark (Vals AI)Not measured6.3%Only GPT-6.1 Sol measured
Excel Modeling Benchmark (Vals AI)Not measured70.8%Only GPT-6.1 Sol measured
BioMysteryBench (Vals AI)Not measured79.6%Only GPT-6.1 Sol measured
Terminal-Bench-Science (Vals AI)Not measured52.9%Only GPT-6.1 Sol measured
Vals Science IndexNot measured59.6%Only GPT-6.1 Sol measured
Robo-bench (Vals AI)Not measured28.3%Only GPT-6.1 Sol measured
τ²-Bench Telecom65.5%Not measuredOnly Gemma 4 31B measured
APEX-AgentsNot measured60.0%Only GPT-6.1 Sol measured
SpireClimbNot measured24.7%Only GPT-6.1 Sol measured
Neither model has a result on the other 20 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index08
Reasoning benchmarks for Gemma 4 31B and GPT-6.1 Sol
BenchmarkGemma 4 31BGPT-6.1 SolLeader
LiveBench reasoning68.3%92.6%GPT-6.1 Sol
MysteryMechanism (Vals AI)Not measured46.4%Only GPT-6.1 Sol measured
GPQA Diamond (Artificial Analysis run)85.7%Not measuredOnly Gemma 4 31B measured
Humanity's Last Exam (Artificial Analysis run)23.6%52.9%GPT-6.1 Sol
GPQA Diamond (Epoch AI run)75.8%95.4%GPT-6.1 Sol
ARC-AGINot measured98.5%Only GPT-6.1 Sol measured
ARC-AGI-2Not measured94.2%Only GPT-6.1 Sol measured
Chess puzzlesNot measured68.0%Only GPT-6.1 Sol measured
Mystery game puzzlesNot measured80.0%Only GPT-6.1 Sol measured
EBR-benchNot measured54.3%Only GPT-6.1 Sol measured
LMArena Text: hard prompts14481463GPT-6.1 Sol
LMArena Text: expert14641489GPT-6.1 Sol
LMArena Text: hard prompts in English14561465GPT-6.1 Sol
LMArena Vision: diagrams12831306GPT-6.1 Sol
LMArena Vision: homework13101356GPT-6.1 Sol
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index03
Math benchmarks for Gemma 4 31B and GPT-6.1 Sol
BenchmarkGemma 4 31BGPT-6.1 SolLeader
OTIS Mock AIME73.3%100.0%GPT-6.1 Sol
FrontierMath, tiers 1 to 3Not measured93.7%Only GPT-6.1 Sol measured
FrontierMath, tier 4Not measured100.0%Only GPT-6.1 Sol measured
ProofBenchNot measured99.0%Only GPT-6.1 Sol measured
LMArena Text: math14631489GPT-6.1 Sol
LMArena Text: mathematical work14651513GPT-6.1 Sol
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index23
Knowledge benchmarks for Gemma 4 31B and GPT-6.1 Sol
BenchmarkGemma 4 31BGPT-6.1 SolLeader
CaseLaw (Vals AI)52.6%Not measuredOnly Gemma 4 31B measured
MortgageTax (Vals AI)61.4%Not measuredOnly Gemma 4 31B measured
MedCode (Vals AI)Not measured48.8%Only GPT-6.1 Sol measured
SimpleQA Verified10.4%73.9%GPT-6.1 Sol
LMArena Text: science14571444Gemma 4 31B
LMArena Text: medicine and healthcare14511433Gemma 4 31B
LMArena Text: legal and government14381471GPT-6.1 Sol
LMArena Text: business and finance14301445GPT-6.1 Sol
Neither model has a result on the other 9 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index01
Web design benchmarks for Gemma 4 31B and GPT-6.1 Sol
BenchmarkGemma 4 31BGPT-6.1 SolLeader
Design Arena: websitesNot measured1321Only GPT-6.1 Sol measured
Design Arena: UI componentsNot measured1321Only GPT-6.1 Sol measured
Design Arena: game devNot measured1389Only GPT-6.1 Sol measured
Design Arena: data vizNot measured1278Only GPT-6.1 Sol measured
Design Arena: 3DNot measured1461Only GPT-6.1 Sol measured
Design Arena: all code categoriesNot measured1345Only GPT-6.1 Sol measured
LiveBench design58.4%82.1%GPT-6.1 Sol
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index517
General benchmarks for Gemma 4 31B and GPT-6.1 Sol
BenchmarkGemma 4 31BGPT-6.1 SolLeader
Vals IndexNot measured63.9%Only GPT-6.1 Sol measured
LiveBench data analysis53.3%82.7%GPT-6.1 Sol
Public Benefits Bench (Vals AI)Not measured59.3%Only GPT-6.1 Sol measured
SAGE (Vals AI)55.0%46.5%Gemma 4 31B
MedScribe (Vals AI)Not measured86.5%Only GPT-6.1 Sol measured
IFBench75.6%Not measuredOnly Gemma 4 31B measured
Long context reasoning (AA-LCR)69.7%84.0%GPT-6.1 Sol
DTBench82.7%96.5%GPT-6.1 Sol
LMCA39.3%62.8%GPT-6.1 Sol
Surface Evolver Bench30.6%Not measuredOnly Gemma 4 31B measured
Furniture assemblyNot measured80.0%Only GPT-6.1 Sol measured
LMArena Text14431443GPT-6.1 Sol
LMArena Text: instruction following14331466GPT-6.1 Sol
LMArena Text: creative writing14171425GPT-6.1 Sol
LMArena Vision12761288GPT-6.1 Sol
LMArena Text: English14511450Gemma 4 31B
LMArena Text: non-English14301433GPT-6.1 Sol
LMArena Text: Chinese14751487GPT-6.1 Sol
LMArena Text: French14361460GPT-6.1 Sol
LMArena Text: Spanish14421439Gemma 4 31B
LMArena Text: Russian14601457Gemma 4 31B
LMArena Text: Polish1433Not measuredOnly Gemma 4 31B measured
LMArena Text: multi-turn14521442Gemma 4 31B
LMArena Text: longer queries14461458GPT-6.1 Sol
LMArena Text: writing and language14321444GPT-6.1 Sol
LMArena Text: entertainment and media14051426GPT-6.1 Sol
LMArena Vision: English12711274GPT-6.1 Sol
LMArena Vision: Chinese1326Not measuredOnly Gemma 4 31B measured
LMArena Vision: reading text12821289GPT-6.1 Sol
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 writing12851301GPT-6.1 Sol
LMArena Document1425Not measuredOnly Gemma 4 31B measured
Neither model has a result on the other 12 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 GPT-6.1 Sol
BenchmarkGemma 4 31BGPT-6.1 SolLeader
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$0.0004Fits in one request
GPT-6.1 Sol$0.0070Fits in one request

Gemma 4 31B costs less

Repository review

50K input + 3K output tokens

Gemma 4 31B$0.011Fits in one request
GPT-6.1 Sol$0.130Fits in one request

Gemma 4 31B costs less

Agent loop

200K input + 10K output tokens

Gemma 4 31B$0.044Fits in one request
GPT-6.1 Sol$0.500Fits 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 GPT-6.1 Sol
SpecificationGoogle Gemma 4 31BOpenAI GPT-6.1 Sol
MakerGoogleOpenAI
WeightsOpen weightsNo public weights listed
ReleasedApril 2, 2026September 29, 2026
Context window262K1.05M
Input $/Mtok$0.20$2.00
Output $/Mtok$0.40$10.00
Coding index38.388.7
Independent measurements behind it22
Cost per solved taskNot computableNot computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemma 4 31B better than GPT-6.1 Sol for coding?

Pick GPT-6.1 Sol for coding: it scores 88.7 on the Vibe Coding Index against 38.3 for Gemma 4 31B. Pick Gemma 4 31B when output tokens cost 25.0x less, or when what matters is LMArena Text: science or LMArena Text: medicine and healthcare, where it leads.

Which is cheaper, Gemma 4 31B or GPT-6.1 Sol?

Gemma 4 31B costs $0.20 per million input tokens and $0.40 per million output tokens; GPT-6.1 Sol costs $2.00 and $10.00. Cost per solved task is known for neither of them.

Which has the bigger context window, Gemma 4 31B or GPT-6.1 Sol?

GPT-6.1 Sol, with 1.05M tokens against 262K.

How many benchmarks is the Gemma 4 31B vs GPT-6.1 Sol 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 GPT-6.1 Sol'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/gemma-4-31b-it-vs-gpt-6-1-sol" title="Gemma 4 31B vs GPT-6.1 Sol, 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-gpt-6-1-sol">LLMBenchmark.ai, Gemma 4 31B vs GPT-6.1 Sol</a></p>