Enter opens the highlighted result. Esc closes.

Claude Opus 5 vs Gemini 3.1 Pro Preview

Claude Opus 5 leads Gemini 3.1 Pro Preview on coding, 83.0 to 32.3 on the Vibe Coding Index, and Gemini 3.1 Pro Preview costs 2.1x less per output token ($12.00 vs $25.00 per million). Updated October 21, 2026; 115 benchmarks have a result for both.

Replace Claude Opus 5 Replace Gemini 3.1 Pro Preview
Claude Opus 5Anthropic
Coding
83.0
Overall
81.6
Output $/M
$25.00
103
Gemini 3.1 Pro PreviewGoogle
Coding
32.3
Overall
54.0
Output $/M
$12.00
11
vs boards won of 115 shared, 1 tied

Claude Opus 5 or Gemini 3.1 Pro Preview: which to pick

Pick Claude Opus 5 for coding: it scores 83.0 on the Vibe Coding Index against 32.3 for Gemini 3.1 Pro Preview.

Pick Gemini 3.1 Pro Preview for output tokens 2.1x cheaper ($12.00 vs $25.00 per million) and a lower cost per solved task ($0.99 against $1.33).

Model AClaude Opus 5Anthropic83.0/1006 independent benchmarks$1.33 per solved taskModel BGemini 3.1 Pro PreviewGoogle32.3/1004 independent benchmarks$0.99 per solved task
Shared results
115
Claude Opus 5 only
16
Gemini 3.1 Pro Preview only
18
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 Opus 5 83.0 from 6 benchmarks, Gemini 3.1 Pro Preview 32.3 from 4 benchmarks.
Widest category
Math, 27.9 points apart on average over 6 shared benchmarks.
Widest single gap
ProofBench: Claude Opus 5 99.0% against Gemini 3.1 Pro Preview 26.0%, 73.0 points apart on a 0 to 100 scale.
Output price
Claude Opus 5 $25.00 against Gemini 3.1 Pro Preview $12.00 per million output tokens, 2.1x apart.
Context window
Claude Opus 5 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 Opus 5BarsGemini 3.1 Pro PreviewTies
Coding182
Intelligence10
Agentic work200
Reasoning125
Math60
Knowledge92
Web design80
General2921 tie
All shared boards103111 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index182
Coding benchmarks for Claude Opus 5 and Gemini 3.1 Pro Preview
BenchmarkClaude Opus 5Gemini 3.1 Pro PreviewLeader
LiveBench coding90.8%Not measuredOnly Claude Opus 5 measured
LMArena WebDev16891447Claude Opus 5
AA Coding Index78.068.8Claude Opus 5
LiveCodeBench (Vals AI)89.0%88.5%Claude Opus 5
SWE-bench Verified (Vals AI)97.0%78.8%Claude Opus 5
Terminal-Bench 4 (Vals AI)53.5%2.5%Claude Opus 5
Vibe Code Bench (Vals AI)88.4%32.0%Claude Opus 5
Code migration (Vals AI)57.5%17.3%Claude Opus 5
ProgramBench (Vals AI)3.0%0.0%Claude Opus 5
IOI (Vals AI)84.3%51.8%Claude Opus 5
Terminal-Bench 2.1 (Vals AI)84.6%70.8%Claude Opus 5
Vibe Code Bench 1-100 (Vals AI)28.5%6.7%Claude Opus 5
SkillsBench (Vals AI)60.4%Not measuredOnly Claude Opus 5 measured
CyberBench (Vals AI)65.4%Not measuredOnly Claude Opus 5 measured
SciCode56.4%58.7%Gemini 3.1 Pro Preview
Terminal-Bench Hard (Artificial Analysis run)Not measured53.8%Only Gemini 3.1 Pro Preview measured
Terminal-BenchNot measured80.2%Only Gemini 3.1 Pro Preview measured
FrontierCode53.4%Not measuredOnly Claude Opus 5 measured
FrontierSWE52.0%Not measuredOnly Claude Opus 5 measured
GSO-BenchNot measured22.6%Only Gemini 3.1 Pro Preview measured
WeirdML91.8%72.1%Claude Opus 5
MirrorCodeNot measured8.9%Only Gemini 3.1 Pro Preview measured
ALE-Bench2164.61160.6Claude Opus 5
LMArena Text: coding15331484Claude Opus 5
LMArena Text: software and IT15271487Claude Opus 5
LMArena WebDev: React17111438Claude Opus 5
LMArena WebDev: HTML16801490Claude Opus 5
LMArena WebDev: from an image16621481Claude Opus 5
SciCode13.8%14.3%Gemini 3.1 Pro Preview
Neither model has a result on the other 10 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
Intelligence benchmarks for Claude Opus 5 and Gemini 3.1 Pro Preview
BenchmarkClaude Opus 5Gemini 3.1 Pro PreviewLeader
AA Intelligence Index50.829.7Claude Opus 5
Epoch Capabilities Index163.9Not measuredOnly Claude Opus 5 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index200
Agentic work benchmarks for Claude Opus 5 and Gemini 3.1 Pro Preview
BenchmarkClaude Opus 5Gemini 3.1 Pro PreviewLeader
AA Agentic Index56.58.2Claude Opus 5
Design Arena: agents building web apps12661125Claude Opus 5
Design Arena: agents building full-stack apps13061068Claude Opus 5
Design Arena: agents building mobile apps13481093Claude Opus 5
Design Arena: agents building Android apps12541048Claude Opus 5
Design Arena: agents building Godot games12791236Claude Opus 5
Design Arena: agents building games12611114Claude Opus 5
Design Arena: HTML slidesNot measured1153Only Gemini 3.1 Pro Preview measured
Design Arena: PowerPoint slides12651066Claude Opus 5
LiveBench research88.9%Not measuredOnly Claude Opus 5 measured
LiveBench browser84.0%Not measuredOnly Claude Opus 5 measured
LiveBench long agentic62.1%Not measuredOnly Claude Opus 5 measured
SREBench (Vals AI)12.2%0.0%Claude Opus 5
Finance Agent (Vals AI)58.6%43.0%Claude Opus 5
Tax Agent Bench (Vals AI)45.5%9.3%Claude Opus 5
Legal Research Bench (Vals AI)55.3%20.7%Claude Opus 5
Excel Modeling Benchmark (Vals AI)73.6%52.6%Claude Opus 5
BioMysteryBench (Vals AI)79.3%60.0%Claude Opus 5
Terminal-Bench-Science (Vals AI)27.1%1.4%Claude Opus 5
Vals Science Index47.9%27.4%Claude Opus 5
Time Horizon Index (Vals AI)18.8%Not measuredOnly Claude Opus 5 measured
CUA-bench (Vals AI)9.0%Not measuredOnly Claude Opus 5 measured
τ²-Bench TelecomNot measured95.6%Only Gemini 3.1 Pro Preview measured
APEX-Agents65.8%35.1%Claude Opus 5
METR time horizonsNot measured77.0%Only Gemini 3.1 Pro Preview measured
OSWorld 2.031.4%Not measuredOnly Claude Opus 5 measured
BALROG63.4%57.0%Claude Opus 5
DeepResearch BenchNot measured47.8%Only Gemini 3.1 Pro Preview measured
PostTrainBench35.0%22.0%Claude Opus 5
Vending-Bench 2$11,182$911Claude Opus 5
LMArena Search1242Not measuredOnly Claude Opus 5 measured
Neither model has a result on the other 10 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index125
Reasoning benchmarks for Claude Opus 5 and Gemini 3.1 Pro Preview
BenchmarkClaude Opus 5Gemini 3.1 Pro PreviewLeader
GPQA Diamond93.4%95.5%Gemini 3.1 Pro Preview
LiveBench reasoning91.2%Not measuredOnly Claude Opus 5 measured
MysteryMechanism (Vals AI)37.4%20.7%Claude Opus 5
MMMU Pro (Vals AI)89.9%88.2%Claude Opus 5
GPQA Diamond (Artificial Analysis run)93.7%94.1%Gemini 3.1 Pro Preview
Humanity's Last Exam (Artificial Analysis run)54.9%47.0%Claude Opus 5
GPQA Diamond (Epoch AI run)93.9%94.4%Gemini 3.1 Pro Preview
ARC-AGI97.5%98.0%Gemini 3.1 Pro Preview
ARC-AGI-290.4%77.1%Claude Opus 5
SimpleBench80.6%79.6%Claude Opus 5
Chess puzzles43.0%51.0%Gemini 3.1 Pro Preview
Mystery game puzzles59.0%34.0%Claude Opus 5
EBR-bench45.7%14.3%Claude Opus 5
LMArena Text: hard prompts15271485Claude Opus 5
LMArena Text: expert15541483Claude Opus 5
LMArena Text: hard prompts in English15231480Claude Opus 5
LMArena Vision: diagrams13481311Claude Opus 5
LMArena Vision: homework13381316Claude Opus 5
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for Claude Opus 5 and Gemini 3.1 Pro Preview
BenchmarkClaude Opus 5Gemini 3.1 Pro PreviewLeader
AIMENot measured98.1%Only Gemini 3.1 Pro Preview measured
OTIS Mock AIME98.9%95.6%Claude Opus 5
FrontierMath, tiers 1 to 385.6%59.6%Claude Opus 5
FrontierMath, tier 473.2%26.8%Claude Opus 5
ProofBench99.0%26.0%Claude Opus 5
LMArena Text: math15331486Claude Opus 5
LMArena Text: mathematical work15441478Claude Opus 5
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index92
Knowledge benchmarks for Claude Opus 5 and Gemini 3.1 Pro Preview
BenchmarkClaude Opus 5Gemini 3.1 Pro PreviewLeader
MMLU Pro91.6%91.0%Claude Opus 5
LegalBench (Vals AI)87.0%87.4%Gemini 3.1 Pro Preview
CaseLaw (Vals AI)Not measured64.8%Only Gemini 3.1 Pro Preview measured
CorpFin (Vals AI)73.2%64.5%Claude Opus 5
TaxEval (Vals AI)75.1%72.9%Claude Opus 5
MortgageTax (Vals AI)72.1%69.4%Claude Opus 5
MedQA (Vals AI)Not measured96.4%Only Gemini 3.1 Pro Preview measured
MedCode (Vals AI)63.6%59.1%Claude Opus 5
SimpleQA Verified59.9%73.5%Gemini 3.1 Pro Preview
LMArena Text: science15311497Claude Opus 5
LMArena Text: medicine and healthcare15251486Claude Opus 5
LMArena Text: legal and government15301487Claude Opus 5
LMArena Text: business and finance15011459Claude Opus 5
FACTS Benchmark SuiteNot measured67.4%Only Gemini 3.1 Pro Preview measured
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for Claude Opus 5 and Gemini 3.1 Pro Preview
BenchmarkClaude Opus 5Gemini 3.1 Pro PreviewLeader
Design Arena: websites13091234Claude Opus 5
Design Arena: UI components13491227Claude Opus 5
Design Arena: game dev13381203Claude Opus 5
Design Arena: data viz13291209Claude Opus 5
Design Arena: 3D13351234Claude Opus 5
Design Arena: all code categories13241231Claude Opus 5
Design Arena: SVG13111285Claude Opus 5
Design Arena: ASCII art13521270Claude Opus 5
LiveBench design83.0%Not measuredOnly Claude Opus 5 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index292
General benchmarks for Claude Opus 5 and Gemini 3.1 Pro Preview
BenchmarkClaude Opus 5Gemini 3.1 Pro PreviewLeader
LiveBench data analysis74.6%Not measuredOnly Claude Opus 5 measured
Public Benefits Bench (Vals AI)76.9%53.8%Claude Opus 5
SAGE (Vals AI)49.4%48.7%Claude Opus 5
MedScribe (Vals AI)91.0%76.1%Claude Opus 5
Vals Multimodal Index73.9%56.1%Claude Opus 5
IFBenchNot measured77.1%Only Gemini 3.1 Pro Preview measured
Long context reasoning (AA-LCR)82.0%82.0%Tie
DTBench97.9%97.1%Claude Opus 5
LMCA64.5%53.8%Claude Opus 5
CL-benchNot measured20.8%Only Gemini 3.1 Pro Preview measured
Furniture assembly60.8%26.7%Claude Opus 5
ExploitBenchNot measured26.1%Only Gemini 3.1 Pro Preview measured
CL-bench LifeNot measured16.9%Only Gemini 3.1 Pro Preview measured
LMArena Text15091480Claude Opus 5
LMArena Text: instruction following15181466Claude Opus 5
LMArena Text: creative writing14931482Claude Opus 5
LMArena Vision13201296Claude Opus 5
LMArena Text: English15081478Claude Opus 5
LMArena Text: non-English15021476Claude Opus 5
LMArena Text: Chinese15731527Claude Opus 5
LMArena Text: German15271490Claude Opus 5
LMArena Text: Japanese15201491Claude Opus 5
LMArena Text: Korean15171455Claude Opus 5
LMArena Text: French15191487Claude Opus 5
LMArena Text: Spanish15231481Claude Opus 5
LMArena Text: Russian15071497Claude Opus 5
LMArena Text: Polish15221498Claude Opus 5
LMArena Text: multi-turn15001487Claude Opus 5
LMArena Text: longer queries15171482Claude Opus 5
LMArena Text: writing and language14991481Claude Opus 5
LMArena Text: entertainment and media14811465Claude Opus 5
LMArena Vision: English13151287Claude Opus 5
LMArena Vision: Chinese14001364Claude Opus 5
LMArena Vision: reading text13291304Claude Opus 5
LMArena Vision: humor12931322Gemini 3.1 Pro Preview
LMArena Vision: captioningNot measured1345Only Gemini 3.1 Pro Preview measured
LMArena Vision: recognizing thingsNot measured1330Only Gemini 3.1 Pro Preview measured
LMArena Vision: creative writing13131324Gemini 3.1 Pro Preview
LMArena Document15161444Claude Opus 5
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 Opus 5 and Gemini 3.1 Pro Preview
BenchmarkClaude Opus 5Gemini 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 Opus 5$0.018Fits 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 Opus 5$0.325Fits 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 Opus 5$1.25Fits 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 Opus 5 and Gemini 3.1 Pro Preview
SpecificationAnthropic Claude Opus 5Google Gemini 3.1 Pro Preview
MakerAnthropicGoogle
WeightsNo public weights listedNo public weights listed
ReleasedJuly 24, 2026February 19, 2026
Context window1M1.05M
Input $/Mtok$5.00$2.00
Output $/Mtok$25.00$12.00
Coding index83.032.3
Independent measurements behind it64
Cost per solved task$1.33$0.99
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 5 better than Gemini 3.1 Pro Preview for coding?

Pick Claude Opus 5 for coding: it scores 83.0 on the Vibe Coding Index against 32.3 for Gemini 3.1 Pro Preview. Pick Gemini 3.1 Pro Preview for output tokens 2.1x cheaper ($12.00 vs $25.00 per million) and a lower cost per solved task ($0.99 against $1.33).

Which is cheaper, Claude Opus 5 or Gemini 3.1 Pro Preview?

Claude Opus 5 costs $5.00 per million input tokens and $25.00 per million output tokens; Gemini 3.1 Pro Preview costs $2.00 and $12.00. Per solved SWE-bench Verified task, Claude Opus 5 costs $1.33 and Gemini 3.1 Pro Preview $0.99.

Which has the bigger context window, Claude Opus 5 or Gemini 3.1 Pro Preview?

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

How many benchmarks is the Claude Opus 5 vs Gemini 3.1 Pro Preview comparison based on?

115 benchmarks have a result for both models as of October 21, 2026. Claude Opus 5's coding index rests on 6 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-opus-5-vs-gemini-3-1-pro-preview" title="Claude Opus 5 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-opus-5-vs-gemini-3-1-pro-preview">LLMBenchmark.ai, Claude Opus 5 vs Gemini 3.1 Pro Preview</a></p>