Enter opens the highlighted result. Esc closes.

Claude Opus 5 vs Gemini 3.5 Flash

Claude Opus 5 leads Gemini 3.5 Flash on coding, 83.0 to 39.8 on the Vibe Coding Index, and Gemini 3.5 Flash costs 2.8x less per output token ($9.00 vs $25.00 per million). Updated October 22, 2026; 106 benchmarks have a result for both.

Replace Claude Opus 5 Replace Gemini 3.5 Flash
Claude Opus 5Anthropic
Coding
83.0
Overall
81.6
Output $/M
$25.00
102
Gemini 3.5 FlashGoogle
Coding
39.8
Overall
63.8
Output $/M
$9.00
4
vs boards won of 106 shared

Claude Opus 5 or Gemini 3.5 Flash: which to pick

Pick Claude Opus 5 for coding: it scores 83.0 on the Vibe Coding Index against 39.8 for Gemini 3.5 Flash.

Pick Gemini 3.5 Flash for output tokens 2.8x cheaper ($9.00 vs $25.00 per million) and a lower cost per solved task ($1.21 against $1.33).

Model AClaude Opus 5Anthropic83.0/1006 independent benchmarks$1.33 per solved taskModel BGemini 3.5 FlashGoogle39.8/1004 independent benchmarks$1.21 per solved task
Shared results
106
Claude Opus 5 only
25
Gemini 3.5 Flash only
6
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 3.5 Flash 39.8 from 4 benchmarks.
Widest category
Math, 25.6 points apart on average over 6 shared benchmarks.
Widest single gap
ProofBench: Claude Opus 5 99.0% against Gemini 3.5 Flash 31.0%, 68.0 points apart on a 0 to 100 scale.
Output price
Claude Opus 5 $25.00 against Gemini 3.5 Flash $9.00 per million output tokens, 2.8x apart.
Context window
Claude Opus 5 takes 1M tokens, Gemini 3.5 Flash 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 3.5 FlashTies
Coding180
Intelligence20
Agentic work140
Reasoning151
Math60
Knowledge101
Web design80
General292
All shared boards1024
CodingLike-for-likeSix of these boards feed the Vibe Coding Index180
Coding benchmarks for Claude Opus 5 and Gemini 3.5 Flash
BenchmarkClaude Opus 5Gemini 3.5 FlashLeader
LiveBench coding90.8%Not measuredOnly Claude Opus 5 measured
LMArena WebDev16891499Claude Opus 5
AA Coding Index78.0Not measuredOnly Claude Opus 5 measured
LiveCodeBench (Vals AI)89.0%87.6%Claude Opus 5
SWE-bench Verified (Vals AI)97.0%78.8%Claude Opus 5
Terminal-Bench 4 (Vals AI)53.5%6.1%Claude Opus 5
Vibe Code Bench (Vals AI)88.4%48.7%Claude Opus 5
Code migration (Vals AI)57.5%26.8%Claude Opus 5
ProgramBench (Vals AI)3.0%0.0%Claude Opus 5
IOI (Vals AI)84.3%Not measuredOnly Claude Opus 5 measured
Terminal-Bench 2.1 (Vals AI)84.6%74.2%Claude Opus 5
Vibe Code Bench 1-100 (Vals AI)28.5%Not measuredOnly Claude Opus 5 measured
SkillsBench (Vals AI)60.4%52.7%Claude Opus 5
CyberBench (Vals AI)65.4%Not measuredOnly Claude Opus 5 measured
SciCode56.4%53.9%Claude Opus 5
Terminal-Bench Hard (Artificial Analysis run)Not measured46.2%Only Gemini 3.5 Flash measured
FrontierCode53.4%Not measuredOnly Claude Opus 5 measured
FrontierSWE52.0%Not measuredOnly Claude Opus 5 measured
WeirdML91.8%62.6%Claude Opus 5
ALE-Bench2164.6911.0Claude Opus 5
LMArena Text: coding15331493Claude Opus 5
LMArena Text: software and IT15271494Claude Opus 5
LMArena WebDev: React17111495Claude Opus 5
LMArena WebDev: HTML16801522Claude Opus 5
LMArena WebDev: from an image16621504Claude Opus 5
SciCode13.8%12.3%Claude Opus 5
Neither model has a result on the other 13 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Opus 5 and Gemini 3.5 Flash
BenchmarkClaude Opus 5Gemini 3.5 FlashLeader
AA Intelligence Index50.833.6Claude Opus 5
Epoch Capabilities Index163.9154.9Claude Opus 5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index140
Agentic work benchmarks for Claude Opus 5 and Gemini 3.5 Flash
BenchmarkClaude Opus 5Gemini 3.5 FlashLeader
AA Agentic Index56.5Not measuredOnly Claude Opus 5 measured
Design Arena: agents building web apps12661202Claude Opus 5
Design Arena: agents building full-stack apps13061197Claude Opus 5
Design Arena: agents building mobile apps13481174Claude Opus 5
Design Arena: agents building Android apps12571185Claude Opus 5
Design Arena: agents building Godot games12791098Claude Opus 5
Design Arena: agents building games12611180Claude Opus 5
Design Arena: HTML slidesNot measured1093Only Gemini 3.5 Flash measured
Design Arena: PowerPoint slides12401154Claude 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%Not measuredOnly Claude Opus 5 measured
Finance Agent (Vals AI)58.6%57.9%Claude Opus 5
Tax Agent Bench (Vals AI)45.5%21.6%Claude Opus 5
Legal Research Bench (Vals AI)55.3%30.8%Claude Opus 5
Excel Modeling Benchmark (Vals AI)73.6%63.5%Claude Opus 5
BioMysteryBench (Vals AI)79.3%Not measuredOnly Claude Opus 5 measured
Terminal-Bench-Science (Vals AI)27.1%5.7%Claude Opus 5
Vals Science Index47.9%Not measuredOnly Claude Opus 5 measured
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 3.5 Flash measured
APEX-Agents65.8%27.5%Claude Opus 5
OSWorld 2.031.4%Not measuredOnly Claude Opus 5 measured
BALROG63.4%Not measuredOnly Claude Opus 5 measured
PostTrainBench35.0%Not measuredOnly Claude Opus 5 measured
Vending-Bench 2$11,182$5,396Claude Opus 5
LMArena Search1242Not measuredOnly Claude Opus 5 measured
Neither model has a result on the other 12 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index151
Reasoning benchmarks for Claude Opus 5 and Gemini 3.5 Flash
BenchmarkClaude Opus 5Gemini 3.5 FlashLeader
GPQA Diamond93.4%92.7%Claude Opus 5
LiveBench reasoning91.2%Not measuredOnly Claude Opus 5 measured
MysteryMechanism (Vals AI)37.4%Not measuredOnly Claude Opus 5 measured
MMMU Pro (Vals AI)89.9%88.3%Claude Opus 5
GPQA Diamond (Artificial Analysis run)93.7%92.2%Claude Opus 5
Humanity's Last Exam (Artificial Analysis run)54.9%42.7%Claude Opus 5
GPQA Diamond (Epoch AI run)93.9%92.8%Claude Opus 5
ARC-AGI97.5%92.5%Claude Opus 5
ARC-AGI-290.4%72.1%Claude Opus 5
SimpleBench80.6%76.7%Claude Opus 5
Chess puzzles43.0%45.0%Gemini 3.5 Flash
Mystery game puzzles59.0%32.0%Claude Opus 5
EBR-bench45.7%4.8%Claude Opus 5
LMArena Text: hard prompts15271488Claude Opus 5
LMArena Text: expert15541495Claude Opus 5
LMArena Text: hard prompts in English15231483Claude Opus 5
LMArena Vision: diagrams13481323Claude Opus 5
LMArena Vision: homework13381330Claude 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 3.5 Flash
BenchmarkClaude Opus 5Gemini 3.5 FlashLeader
OTIS Mock AIME98.9%95.6%Claude Opus 5
FrontierMath, tiers 1 to 385.6%62.8%Claude Opus 5
FrontierMath, tier 473.2%26.8%Claude Opus 5
ProofBench99.0%31.0%Claude Opus 5
LMArena Text: math15331504Claude Opus 5
LMArena Text: mathematical work15441495Claude Opus 5
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index101
Knowledge benchmarks for Claude Opus 5 and Gemini 3.5 Flash
BenchmarkClaude Opus 5Gemini 3.5 FlashLeader
MMLU Pro91.6%89.5%Claude Opus 5
LegalBench (Vals AI)87.0%83.6%Claude Opus 5
CorpFin (Vals AI)73.2%64.7%Claude Opus 5
TaxEval (Vals AI)75.1%74.4%Claude Opus 5
MortgageTax (Vals AI)72.1%68.1%Claude Opus 5
MedCode (Vals AI)63.6%55.8%Claude Opus 5
SimpleQA Verified59.9%66.2%Gemini 3.5 Flash
LMArena Text: science15311495Claude Opus 5
LMArena Text: medicine and healthcare15251483Claude Opus 5
LMArena Text: legal and government15301488Claude Opus 5
LMArena Text: business and finance15011467Claude Opus 5
FACTS Benchmark SuiteNot measured63.1%Only Gemini 3.5 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 index80
Web design benchmarks for Claude Opus 5 and Gemini 3.5 Flash
BenchmarkClaude Opus 5Gemini 3.5 FlashLeader
Design Arena: websites13091267Claude Opus 5
Design Arena: UI components13461269Claude Opus 5
Design Arena: game dev13371263Claude Opus 5
Design Arena: data viz13291236Claude Opus 5
Design Arena: 3D13341243Claude Opus 5
Design Arena: all code categories13231266Claude Opus 5
Design Arena: SVG13111253Claude Opus 5
Design Arena: ASCII art13521254Claude 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 3.5 Flash
BenchmarkClaude Opus 5Gemini 3.5 FlashLeader
LiveBench data analysis74.6%Not measuredOnly Claude Opus 5 measured
Public Benefits Bench (Vals AI)76.9%59.5%Claude Opus 5
SAGE (Vals AI)49.4%49.9%Gemini 3.5 Flash
MedScribe (Vals AI)91.0%76.6%Claude Opus 5
Vals Multimodal Index73.9%62.9%Claude Opus 5
IFBenchNot measured76.3%Only Gemini 3.5 Flash measured
Long context reasoning (AA-LCR)82.0%74.3%Claude Opus 5
DTBench97.9%94.7%Claude Opus 5
LMCA64.5%47.1%Claude Opus 5
Surface Evolver BenchNot measured58.1%Only Gemini 3.5 Flash measured
Furniture assembly60.8%Not measuredOnly Claude Opus 5 measured
LMArena Text15091482Claude Opus 5
LMArena Text: instruction following15181467Claude Opus 5
LMArena Text: creative writing14931470Claude Opus 5
LMArena Vision13201308Claude Opus 5
LMArena Text: English15081481Claude Opus 5
LMArena Text: non-English15021475Claude Opus 5
LMArena Text: Chinese15731527Claude Opus 5
LMArena Text: German15271494Claude Opus 5
LMArena Text: Japanese15201486Claude Opus 5
LMArena Text: Korean15171448Claude Opus 5
LMArena Text: French15191490Claude Opus 5
LMArena Text: Spanish15231480Claude Opus 5
LMArena Text: Russian15071493Claude Opus 5
LMArena Text: Polish15221516Claude Opus 5
LMArena Text: multi-turn15001481Claude Opus 5
LMArena Text: longer queries15171483Claude Opus 5
LMArena Text: writing and language14991478Claude Opus 5
LMArena Text: entertainment and media14811459Claude Opus 5
LMArena Vision: English13151305Claude Opus 5
LMArena Vision: Chinese14001377Claude Opus 5
LMArena Vision: reading text13291317Claude Opus 5
LMArena Vision: humor12931321Gemini 3.5 Flash
LMArena Vision: creative writing13131301Claude Opus 5
LMArena Document15161463Claude Opus 5
Neither model has a result on the other 11 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 3.5 Flash
BenchmarkClaude Opus 5Gemini 3.5 FlashLeader
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 3.5 Flash$0.0060Fits in one request

Gemini 3.5 Flash costs less

Repository review

50K input + 3K output tokens

Claude Opus 5$0.325Fits in one request
Gemini 3.5 Flash$0.102Fits in one request

Gemini 3.5 Flash costs less

Agent loop

200K input + 10K output tokens

Claude Opus 5$1.25Fits in one request
Gemini 3.5 Flash$0.390Fits in one request

Gemini 3.5 Flash 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 3.5 Flash
SpecificationAnthropic Claude Opus 5Google Gemini 3.5 Flash
MakerAnthropicGoogle
WeightsNo public weights listedNo public weights listed
ReleasedJuly 24, 2026May 19, 2026
Context window1M1.05M
Input $/Mtok$5.00$1.50
Output $/Mtok$25.00$9.00
Coding index83.039.8
Independent measurements behind it64
Cost per solved task$1.33$1.21
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 5 better than Gemini 3.5 Flash for coding?

Pick Claude Opus 5 for coding: it scores 83.0 on the Vibe Coding Index against 39.8 for Gemini 3.5 Flash. Pick Gemini 3.5 Flash for output tokens 2.8x cheaper ($9.00 vs $25.00 per million) and a lower cost per solved task ($1.21 against $1.33).

Which is cheaper, Claude Opus 5 or Gemini 3.5 Flash?

Claude Opus 5 costs $5.00 per million input tokens and $25.00 per million output tokens; Gemini 3.5 Flash costs $1.50 and $9.00. Per solved SWE-bench Verified task, Claude Opus 5 costs $1.33 and Gemini 3.5 Flash $1.21.

Which has the bigger context window, Claude Opus 5 or Gemini 3.5 Flash?

Gemini 3.5 Flash, with 1.05M tokens against 1M.

How many benchmarks is the Claude Opus 5 vs Gemini 3.5 Flash comparison based on?

106 benchmarks have a result for both models as of October 22, 2026. Claude Opus 5's coding index rests on 6 independent benchmarks and Gemini 3.5 Flash'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-3-5-flash" title="Claude Opus 5 vs Gemini 3.5 Flash, 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-3-5-flash">LLMBenchmark.ai, Claude Opus 5 vs Gemini 3.5 Flash</a></p>