Enter opens the highlighted result. Esc closes.

Claude Sonnet 4.6 vs Gemini 3.1 Pro Preview

Claude Sonnet 4.6 leads Gemini 3.1 Pro Preview on coding, 57.3 to 32.3 on the Vibe Coding Index, and Gemini 3.1 Pro Preview costs 1.3x less per output token ($12.00 vs $15.00 per million). Updated October 22, 2026; 106 benchmarks have a result for both.

Replace Claude Sonnet 4.6 Replace Gemini 3.1 Pro Preview
Claude Sonnet 4.6Anthropic
Coding
57.3
Overall
60.3
Output $/M
$15.00
40
Gemini 3.1 Pro PreviewGoogle
Coding
32.3
Overall
54.0
Output $/M
$12.00
65
vs boards won of 106 shared, 1 tied

Claude Sonnet 4.6 or Gemini 3.1 Pro Preview: which to pick

Pick Claude Sonnet 4.6 for coding: it scores 57.3 on the Vibe Coding Index against 32.3 for Gemini 3.1 Pro Preview.

Pick Gemini 3.1 Pro Preview for output tokens 1.3x cheaper ($12.00 vs $15.00 per million) and a lower cost per solved task ($0.99 against $1.68).

Model AClaude Sonnet 4.6Anthropic57.3/1005 independent benchmarks$1.68 per solved taskModel BGemini 3.1 Pro PreviewGoogle32.3/1004 independent benchmarks$0.99 per solved task
Shared results
106
Claude Sonnet 4.6 only
12
Gemini 3.1 Pro Preview only
27
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
Claude Sonnet 4.6 57.3 from 5 benchmarks, Gemini 3.1 Pro Preview 32.3 from 4 benchmarks.
Widest category
Agentic work, 14.2 points apart on average over 15 shared benchmarks.
Widest single gap
Vending-Bench 2: Claude Sonnet 4.6 $7,204 against Gemini 3.1 Pro Preview $911, 39.3 points apart on a 0 to 100 scale.
Output price
Claude Sonnet 4.6 $15.00 against Gemini 3.1 Pro Preview $12.00 per million output tokens, 1.3x apart.
Context window
Claude Sonnet 4.6 takes 1M tokens, Gemini 3.1 Pro Preview 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
CategoryClaude Sonnet 4.6BarsGemini 3.1 Pro PreviewTies
Coding98
Intelligence10
Agentic work132
Reasoning212
Math23
Knowledge310
Web design521 tie
General528
All shared boards40651 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index98
Coding benchmarks for Claude Sonnet 4.6 and Gemini 3.1 Pro Preview
BenchmarkClaude Sonnet 4.6Gemini 3.1 Pro PreviewLeader
LiveBench coding66.6%Not measuredOnly Claude Sonnet 4.6 measured
LMArena WebDev15231447Claude Sonnet 4.6
AA Coding Index63.068.8Gemini 3.1 Pro Preview
LiveCodeBench (Vals AI)82.1%88.5%Gemini 3.1 Pro Preview
SWE-bench Verified (Vals AI)77.4%78.8%Gemini 3.1 Pro Preview
Terminal-Bench 4 (Vals AI)Not measured2.5%Only Gemini 3.1 Pro Preview measured
Vibe Code Bench (Vals AI)55.8%32.0%Claude Sonnet 4.6
Code migration (Vals AI)39.9%17.3%Claude Sonnet 4.6
ProgramBench (Vals AI)0.5%0.0%Claude Sonnet 4.6
IOI (Vals AI)Not measured51.8%Only Gemini 3.1 Pro Preview measured
Terminal-Bench 2.1 (Vals AI)57.3%70.8%Gemini 3.1 Pro Preview
Vibe Code Bench 1-100 (Vals AI)Not measured6.7%Only Gemini 3.1 Pro Preview measured
SkillsBench (Vals AI)49.0%Not measuredOnly Claude Sonnet 4.6 measured
SciCode50.1%58.7%Gemini 3.1 Pro Preview
Terminal-Bench Hard (Artificial Analysis run)53.0%53.8%Gemini 3.1 Pro Preview
Terminal-Bench53.4%80.2%Gemini 3.1 Pro Preview
FrontierCode24.3%Not measuredOnly Claude Sonnet 4.6 measured
GSO-BenchNot measured22.6%Only Gemini 3.1 Pro Preview measured
WeirdML66.1%72.1%Gemini 3.1 Pro Preview
MirrorCodeNot measured8.9%Only Gemini 3.1 Pro Preview measured
ALE-BenchNot measured1160.6Only Gemini 3.1 Pro Preview measured
LMArena Text: coding15031484Claude Sonnet 4.6
LMArena Text: software and IT14911487Claude Sonnet 4.6
LMArena WebDev: React15121438Claude Sonnet 4.6
LMArena WebDev: HTML15271490Claude Sonnet 4.6
LMArena WebDev: from an image15291481Claude Sonnet 4.6
SciCodeNot measured14.3%Only Gemini 3.1 Pro Preview measured
Neither model has a result on the other 12 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Claude Sonnet 4.6 and Gemini 3.1 Pro Preview
BenchmarkClaude Sonnet 4.6Gemini 3.1 Pro PreviewLeader
AA Intelligence Index30.129.7Claude Sonnet 4.6
Epoch Capabilities Index152.8Not measuredOnly Claude Sonnet 4.6 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index132
Agentic work benchmarks for Claude Sonnet 4.6 and Gemini 3.1 Pro Preview
BenchmarkClaude Sonnet 4.6Gemini 3.1 Pro PreviewLeader
AA Agentic Index31.88.2Claude Sonnet 4.6
Design Arena: agents building web apps11901125Claude Sonnet 4.6
Design Arena: agents building full-stack apps12131068Claude Sonnet 4.6
Design Arena: agents building mobile apps12121094Claude Sonnet 4.6
Design Arena: agents building Android apps11971049Claude Sonnet 4.6
Design Arena: agents building Godot games12261236Gemini 3.1 Pro Preview
Design Arena: agents building games11771113Claude Sonnet 4.6
Design Arena: HTML slidesNot measured1103Only Gemini 3.1 Pro Preview measured
Design Arena: PowerPoint slidesNot measured1041Only Gemini 3.1 Pro Preview measured
LiveBench research63.6%Not measuredOnly Claude Sonnet 4.6 measured
LiveBench browser68.0%Not measuredOnly Claude Sonnet 4.6 measured
LiveBench long agentic23.1%Not measuredOnly Claude Sonnet 4.6 measured
SREBench (Vals AI)Not measured0.0%Only Gemini 3.1 Pro Preview measured
Finance Agent (Vals AI)51.0%43.0%Claude Sonnet 4.6
Tax Agent Bench (Vals AI)25.8%9.3%Claude Sonnet 4.6
Legal Research Bench (Vals AI)38.5%20.7%Claude Sonnet 4.6
Excel Modeling Benchmark (Vals AI)60.2%52.6%Claude Sonnet 4.6
BioMysteryBench (Vals AI)Not measured60.0%Only Gemini 3.1 Pro Preview measured
Terminal-Bench-Science (Vals AI)Not measured1.4%Only Gemini 3.1 Pro Preview measured
Vals Science IndexNot measured27.4%Only Gemini 3.1 Pro Preview measured
τ²-Bench Telecom79.5%95.6%Gemini 3.1 Pro Preview
APEX-Agents43.0%35.1%Claude Sonnet 4.6
METR time horizonsNot measured77.0%Only Gemini 3.1 Pro Preview measured
OSWorld 2.09.3%Not measuredOnly Claude Sonnet 4.6 measured
BALROGNot measured57.0%Only Gemini 3.1 Pro Preview measured
DeepResearch Bench54.9%47.8%Claude Sonnet 4.6
PostTrainBenchNot measured22.0%Only Gemini 3.1 Pro Preview measured
OSWorld72.1%Not measuredOnly Claude Sonnet 4.6 measured
Vending-Bench 2$7,204$911Claude Sonnet 4.6
Neither model has a result on the other 12 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index212
Reasoning benchmarks for Claude Sonnet 4.6 and Gemini 3.1 Pro Preview
BenchmarkClaude Sonnet 4.6Gemini 3.1 Pro PreviewLeader
GPQA Diamond85.6%95.5%Gemini 3.1 Pro Preview
LiveBench reasoning86.4%Not measuredOnly Claude Sonnet 4.6 measured
MysteryMechanism (Vals AI)Not measured20.7%Only Gemini 3.1 Pro Preview measured
MMMU Pro (Vals AI)83.6%88.2%Gemini 3.1 Pro Preview
GPQA Diamond (Artificial Analysis run)87.5%94.1%Gemini 3.1 Pro Preview
Humanity's Last Exam (Artificial Analysis run)33.6%47.0%Gemini 3.1 Pro Preview
GPQA Diamond (Epoch AI run)87.4%94.4%Gemini 3.1 Pro Preview
ARC-AGI86.5%98.0%Gemini 3.1 Pro Preview
ARC-AGI-260.4%77.1%Gemini 3.1 Pro Preview
SimpleBenchNot measured79.6%Only Gemini 3.1 Pro Preview measured
Chess puzzles23.0%51.0%Gemini 3.1 Pro Preview
Mystery game puzzles16.0%34.0%Gemini 3.1 Pro Preview
EBR-benchNot measured14.3%Only Gemini 3.1 Pro Preview measured
LMArena Text: hard prompts14851485Gemini 3.1 Pro Preview
LMArena Text: expert15001483Claude Sonnet 4.6
LMArena Text: hard prompts in English14931480Claude Sonnet 4.6
LMArena Vision: diagrams13061311Gemini 3.1 Pro Preview
LMArena Vision: homework13111316Gemini 3.1 Pro Preview
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index23
Math benchmarks for Claude Sonnet 4.6 and Gemini 3.1 Pro Preview
BenchmarkClaude Sonnet 4.6Gemini 3.1 Pro PreviewLeader
AIME92.3%98.1%Gemini 3.1 Pro Preview
OTIS Mock AIME85.8%95.6%Gemini 3.1 Pro Preview
FrontierMath, tiers 1 to 3Not measured59.6%Only Gemini 3.1 Pro Preview measured
FrontierMath, tier 4Not measured26.8%Only Gemini 3.1 Pro Preview measured
ProofBench45.0%26.0%Claude Sonnet 4.6
LMArena Text: math14621486Gemini 3.1 Pro Preview
LMArena Text: mathematical work14831478Claude Sonnet 4.6
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index310
Knowledge benchmarks for Claude Sonnet 4.6 and Gemini 3.1 Pro Preview
BenchmarkClaude Sonnet 4.6Gemini 3.1 Pro PreviewLeader
MMLU Pro87.3%91.0%Gemini 3.1 Pro Preview
LegalBench (Vals AI)82.1%87.4%Gemini 3.1 Pro Preview
CaseLaw (Vals AI)64.0%64.8%Gemini 3.1 Pro Preview
CorpFin (Vals AI)65.3%64.5%Claude Sonnet 4.6
TaxEval (Vals AI)77.1%72.9%Claude Sonnet 4.6
MortgageTax (Vals AI)67.7%69.4%Gemini 3.1 Pro Preview
MedQA (Vals AI)92.1%96.4%Gemini 3.1 Pro Preview
MedCode (Vals AI)Not measured59.1%Only Gemini 3.1 Pro Preview measured
SimpleQA Verified35.5%73.5%Gemini 3.1 Pro Preview
LMArena Text: science14741497Gemini 3.1 Pro Preview
LMArena Text: medicine and healthcare14511486Gemini 3.1 Pro Preview
LMArena Text: legal and government14701487Gemini 3.1 Pro Preview
LMArena Text: business and finance14641459Claude Sonnet 4.6
FACTS Benchmark Suite37.0%67.4%Gemini 3.1 Pro Preview
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index52
Web design benchmarks for Claude Sonnet 4.6 and Gemini 3.1 Pro Preview
BenchmarkClaude Sonnet 4.6Gemini 3.1 Pro PreviewLeader
Design Arena: websites12841233Claude Sonnet 4.6
Design Arena: UI components12691224Claude Sonnet 4.6
Design Arena: game dev12581202Claude Sonnet 4.6
Design Arena: data viz12781209Claude Sonnet 4.6
Design Arena: 3D12341234Tie
Design Arena: all code categories12751231Claude Sonnet 4.6
Design Arena: SVG11961285Gemini 3.1 Pro Preview
Design Arena: ASCII art12351270Gemini 3.1 Pro Preview
LiveBench design71.8%Not measuredOnly Claude Sonnet 4.6 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index528
General benchmarks for Claude Sonnet 4.6 and Gemini 3.1 Pro Preview
BenchmarkClaude Sonnet 4.6Gemini 3.1 Pro PreviewLeader
LiveBench data analysis76.1%Not measuredOnly Claude Sonnet 4.6 measured
Public Benefits Bench (Vals AI)62.5%53.8%Claude Sonnet 4.6
SAGE (Vals AI)46.6%48.7%Gemini 3.1 Pro Preview
MedScribe (Vals AI)Not measured76.1%Only Gemini 3.1 Pro Preview measured
Vals Multimodal Index60.6%56.1%Claude Sonnet 4.6
IFBench56.6%77.1%Gemini 3.1 Pro Preview
Long context reasoning (AA-LCR)80.0%82.0%Gemini 3.1 Pro Preview
DTBench89.9%97.1%Gemini 3.1 Pro Preview
LMCA46.5%53.8%Gemini 3.1 Pro Preview
CL-benchNot measured20.8%Only Gemini 3.1 Pro Preview measured
Furniture assemblyNot measured26.7%Only Gemini 3.1 Pro Preview measured
ExploitBench23.6%26.1%Gemini 3.1 Pro Preview
CL-bench LifeNot measured16.9%Only Gemini 3.1 Pro Preview measured
LMArena Text14581480Gemini 3.1 Pro Preview
LMArena Text: instruction following14761466Claude Sonnet 4.6
LMArena Text: creative writing14351482Gemini 3.1 Pro Preview
LMArena Vision12831296Gemini 3.1 Pro Preview
LMArena Text: English14721478Gemini 3.1 Pro Preview
LMArena Text: non-English14401476Gemini 3.1 Pro Preview
LMArena Text: Chinese14911527Gemini 3.1 Pro Preview
LMArena Text: German14281490Gemini 3.1 Pro Preview
LMArena Text: Japanese14201491Gemini 3.1 Pro Preview
LMArena Text: Korean14101455Gemini 3.1 Pro Preview
LMArena Text: French14651487Gemini 3.1 Pro Preview
LMArena Text: Spanish14641481Gemini 3.1 Pro Preview
LMArena Text: Russian14401497Gemini 3.1 Pro Preview
LMArena Text: Polish14431498Gemini 3.1 Pro Preview
LMArena Text: multi-turn14641487Gemini 3.1 Pro Preview
LMArena Text: longer queries14791482Gemini 3.1 Pro Preview
LMArena Text: writing and language14441481Gemini 3.1 Pro Preview
LMArena Text: entertainment and media14311465Gemini 3.1 Pro Preview
LMArena Vision: English12981287Claude Sonnet 4.6
LMArena Vision: Chinese13071364Gemini 3.1 Pro Preview
LMArena Vision: reading text12961304Gemini 3.1 Pro Preview
LMArena Vision: humor12481322Gemini 3.1 Pro Preview
LMArena Vision: captioningNot measured1345Only Gemini 3.1 Pro Preview measured
LMArena Vision: recognizing things11951330Gemini 3.1 Pro Preview
LMArena Vision: creative writing12721324Gemini 3.1 Pro Preview
LMArena Document14821444Claude Sonnet 4.6
Neither model has a result on the other 7 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Sonnet 4.6 and Gemini 3.1 Pro Preview
BenchmarkClaude Sonnet 4.6Gemini 3.1 Pro PreviewLeader
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

Claude Sonnet 4.6$0.011Fits in one request
Gemini 3.1 Pro Preview$0.0080Fits in one request

Gemini 3.1 Pro Preview costs less

Repository review

50K input + 3K output tokens

Claude Sonnet 4.6$0.195Fits in one request
Gemini 3.1 Pro Preview$0.136Fits in one request

Gemini 3.1 Pro Preview costs less

Agent loop

200K input + 10K output tokens

Claude Sonnet 4.6$0.750Fits in one request
Gemini 3.1 Pro Preview$0.520Fits in one request

Gemini 3.1 Pro Preview 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 Claude Sonnet 4.6 and Gemini 3.1 Pro Preview
SpecificationAnthropic Claude Sonnet 4.6Google Gemini 3.1 Pro Preview
MakerAnthropicGoogle
WeightsNo public weights listedNo public weights listed
ReleasedFebruary 17, 2026February 19, 2026
Context window1M1.05M
Input $/Mtok$3.00$2.00
Output $/Mtok$15.00$12.00
Coding index57.332.3
Independent measurements behind it54
Cost per solved task$1.68$0.99
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Sonnet 4.6 better than Gemini 3.1 Pro Preview for coding?

Pick Claude Sonnet 4.6 for coding: it scores 57.3 on the Vibe Coding Index against 32.3 for Gemini 3.1 Pro Preview. Pick Gemini 3.1 Pro Preview for output tokens 1.3x cheaper ($12.00 vs $15.00 per million) and a lower cost per solved task ($0.99 against $1.68).

Which is cheaper, Claude Sonnet 4.6 or Gemini 3.1 Pro Preview?

Claude Sonnet 4.6 costs $3.00 per million input tokens and $15.00 per million output tokens; Gemini 3.1 Pro Preview costs $2.00 and $12.00. Per solved SWE-bench Verified task, Claude Sonnet 4.6 costs $1.68 and Gemini 3.1 Pro Preview $0.99.

Which has the bigger context window, Claude Sonnet 4.6 or Gemini 3.1 Pro Preview?

Gemini 3.1 Pro Preview, with 1.05M tokens against 1M.

How many benchmarks is the Claude Sonnet 4.6 vs Gemini 3.1 Pro Preview comparison based on?

106 benchmarks have a result for both models as of October 22, 2026. Claude Sonnet 4.6's coding index rests on 5 independent benchmarks and Gemini 3.1 Pro Preview's on 4. 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/claude-sonnet-4-6-vs-gemini-3-1-pro-preview" title="Claude Sonnet 4.6 vs Gemini 3.1 Pro Preview, 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/claude-sonnet-4-6-vs-gemini-3-1-pro-preview">LLMBenchmark.ai, Claude Sonnet 4.6 vs Gemini 3.1 Pro Preview</a></p>