Enter opens the highlighted result. Esc closes.

Claude Opus 4.8 vs Gemini 3.5 Flash

Claude Opus 4.8 leads Gemini 3.5 Flash on coding, 65.0 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 21, 2026; 110 benchmarks have a result for both.

Replace Claude Opus 4.8 Replace Gemini 3.5 Flash
Claude Opus 4.8Anthropic
Coding
65.0
Overall
69.8
Output $/M
$25.00
58
Gemini 3.5 FlashGoogle
Coding
39.8
Overall
63.8
Output $/M
$9.00
49
vs boards won of 110 shared, 3 tied

Claude Opus 4.8 or Gemini 3.5 Flash: which to pick

Pick Claude Opus 4.8 for coding: it scores 65.0 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 $2.17).

Model AClaude Opus 4.8Anthropic65.0/1006 independent benchmarks$2.17 per solved taskModel BGemini 3.5 FlashGoogle39.8/1004 independent benchmarks$1.21 per solved task
Shared results
110
Claude Opus 4.8 only
20
Gemini 3.5 Flash only
2
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 4.8 65.0 from 6 benchmarks, Gemini 3.5 Flash 39.8 from 4 benchmarks.
Widest category
Math, 15.1 points apart on average over 6 shared benchmarks.
Widest single gap
ProofBench: Claude Opus 4.8 69.0% against Gemini 3.5 Flash 31.0%, 38.0 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.8 $25.00 against Gemini 3.5 Flash $9.00 per million output tokens, 2.8x apart.
Context window
Claude Opus 4.8 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 4.8BarsGemini 3.5 FlashTies
Coding1331 tie
Intelligence20
Agentic work133
Reasoning772 ties
Math51
Knowledge48
Web design35
General1122
All shared boards58493 ties
CodingLike-for-likeSix of these boards feed the Vibe Coding Index133
Coding benchmarks for Claude Opus 4.8 and Gemini 3.5 Flash
BenchmarkClaude Opus 4.8Gemini 3.5 FlashLeader
LiveBench coding77.3%Not measuredOnly Claude Opus 4.8 measured
LMArena WebDev15561499Claude Opus 4.8
AA Coding Index74.3Not measuredOnly Claude Opus 4.8 measured
LiveCodeBench (Vals AI)87.8%87.6%Claude Opus 4.8
SWE-bench Verified (Vals AI)88.6%78.8%Claude Opus 4.8
Terminal-Bench 4 (Vals AI)23.2%6.1%Claude Opus 4.8
Vibe Code Bench (Vals AI)82.7%48.7%Claude Opus 4.8
Code migration (Vals AI)47.3%26.8%Claude Opus 4.8
ProgramBench (Vals AI)1.0%0.0%Claude Opus 4.8
Terminal-Bench 2.1 (Vals AI)71.9%74.2%Gemini 3.5 Flash
SkillsBench (Vals AI)59.2%52.7%Claude Opus 4.8
SciCode54.4%53.9%Claude Opus 4.8
Terminal-Bench Hard (Artificial Analysis run)58.3%46.2%Claude Opus 4.8
FrontierCode46.5%Not measuredOnly Claude Opus 4.8 measured
GSO-Bench47.1%Not measuredOnly Claude Opus 4.8 measured
WeirdML82.9%62.6%Claude Opus 4.8
ALE-BenchNot measured911.0Only Gemini 3.5 Flash measured
LMArena Text: coding14901493Gemini 3.5 Flash
LMArena Text: software and IT14881494Gemini 3.5 Flash
LMArena WebDev: React15571495Claude Opus 4.8
LMArena WebDev: HTML15431522Claude Opus 4.8
LMArena WebDev: from an imageNot measured1504Only Gemini 3.5 Flash measured
SciCode12.3%12.3%Tie
Neither model has a result on the other 16 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Opus 4.8 and Gemini 3.5 Flash
BenchmarkClaude Opus 4.8Gemini 3.5 FlashLeader
AA Intelligence Index41.833.6Claude Opus 4.8
Epoch Capabilities Index159.0154.9Claude Opus 4.8
Agentic workLike-for-likePublic boards, shown as published, kept out of the index133
Agentic work benchmarks for Claude Opus 4.8 and Gemini 3.5 Flash
BenchmarkClaude Opus 4.8Gemini 3.5 FlashLeader
AA Agentic Index41.9Not measuredOnly Claude Opus 4.8 measured
Design Arena: agents building web apps12331202Claude Opus 4.8
Design Arena: agents building full-stack apps12491197Claude Opus 4.8
Design Arena: agents building mobile apps12221174Claude Opus 4.8
Design Arena: agents building Android apps12321184Claude Opus 4.8
Design Arena: agents building Godot games12311098Claude Opus 4.8
Design Arena: agents building games12381180Claude Opus 4.8
Design Arena: HTML slides12211142Claude Opus 4.8
Design Arena: PowerPoint slides12271179Claude Opus 4.8
Design Arena: spreadsheets1270Not measuredOnly Claude Opus 4.8 measured
LiveBench research81.8%Not measuredOnly Claude Opus 4.8 measured
LiveBench browser96.0%Not measuredOnly Claude Opus 4.8 measured
LiveBench long agentic48.3%Not measuredOnly Claude Opus 4.8 measured
Finance Agent (Vals AI)53.9%57.9%Gemini 3.5 Flash
Tax Agent Bench (Vals AI)30.0%21.6%Claude Opus 4.8
Legal Research Bench (Vals AI)43.8%30.8%Claude Opus 4.8
Excel Modeling Benchmark (Vals AI)69.4%63.5%Claude Opus 4.8
Terminal-Bench-Science (Vals AI)4.3%5.7%Gemini 3.5 Flash
Time Horizon Index (Vals AI)11.8%Not measuredOnly Claude Opus 4.8 measured
τ²-Bench Telecom94.4%95.6%Gemini 3.5 Flash
APEX-Agents48.9%27.5%Claude Opus 4.8
Remote Labor Index8.3%Not measuredOnly Claude Opus 4.8 measured
OSWorld 2.020.6%Not measuredOnly Claude Opus 4.8 measured
DeepResearch Bench50.2%Not measuredOnly Claude Opus 4.8 measured
PostTrainBench33.8%Not measuredOnly Claude Opus 4.8 measured
Vending-Bench 2$5,787$5,396Claude Opus 4.8
LMArena Search1204Not measuredOnly Claude Opus 4.8 measured
Neither model has a result on the other 14 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index77
Reasoning benchmarks for Claude Opus 4.8 and Gemini 3.5 Flash
BenchmarkClaude Opus 4.8Gemini 3.5 FlashLeader
GPQA Diamond92.4%92.7%Gemini 3.5 Flash
LiveBench reasoning89.2%Not measuredOnly Claude Opus 4.8 measured
MMMU Pro (Vals AI)86.6%88.3%Gemini 3.5 Flash
GPQA Diamond (Artificial Analysis run)92.0%92.2%Gemini 3.5 Flash
Humanity's Last Exam (Artificial Analysis run)48.7%42.7%Claude Opus 4.8
GPQA Diamond (Epoch AI run)91.0%92.8%Gemini 3.5 Flash
ARC-AGI92.5%92.5%Tie
ARC-AGI-272.1%72.1%Tie
SimpleBench64.8%76.7%Gemini 3.5 Flash
Chess puzzles52.0%45.0%Claude Opus 4.8
Mystery game puzzles36.0%32.0%Claude Opus 4.8
EBR-bench28.6%4.8%Claude Opus 4.8
LMArena Text: hard prompts14821488Gemini 3.5 Flash
LMArena Text: expert15031495Claude Opus 4.8
LMArena Text: hard prompts in English14871483Claude Opus 4.8
LMArena Vision: diagrams13151323Gemini 3.5 Flash
LMArena Vision: homework13371330Claude Opus 4.8
Kagi LLM Benchmark88.8%Not measuredOnly Claude Opus 4.8 measured
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index51
Math benchmarks for Claude Opus 4.8 and Gemini 3.5 Flash
BenchmarkClaude Opus 4.8Gemini 3.5 FlashLeader
OTIS Mock AIME98.3%95.6%Claude Opus 4.8
FrontierMath, tiers 1 to 380.0%62.8%Claude Opus 4.8
FrontierMath, tier 456.1%26.8%Claude Opus 4.8
ProofBench69.0%31.0%Claude Opus 4.8
LMArena Text: math14861504Gemini 3.5 Flash
LMArena Text: mathematical work14971495Claude Opus 4.8
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index48
Knowledge benchmarks for Claude Opus 4.8 and Gemini 3.5 Flash
BenchmarkClaude Opus 4.8Gemini 3.5 FlashLeader
MMLU Pro89.6%89.5%Claude Opus 4.8
LegalBench (Vals AI)83.6%83.6%Gemini 3.5 Flash
CorpFin (Vals AI)66.7%64.7%Claude Opus 4.8
TaxEval (Vals AI)75.6%74.4%Claude Opus 4.8
MortgageTax (Vals AI)69.9%68.1%Claude Opus 4.8
MedCode (Vals AI)53.2%55.8%Gemini 3.5 Flash
SimpleQA Verified53.0%66.2%Gemini 3.5 Flash
LMArena Text: science14771495Gemini 3.5 Flash
LMArena Text: medicine and healthcare14641483Gemini 3.5 Flash
LMArena Text: legal and government14771488Gemini 3.5 Flash
LMArena Text: business and finance14581467Gemini 3.5 Flash
FACTS Benchmark Suite53.5%63.1%Gemini 3.5 Flash
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index35
Web design benchmarks for Claude Opus 4.8 and Gemini 3.5 Flash
BenchmarkClaude Opus 4.8Gemini 3.5 FlashLeader
Design Arena: websites12591268Gemini 3.5 Flash
Design Arena: UI components12571273Gemini 3.5 Flash
Design Arena: game dev12641263Claude Opus 4.8
Design Arena: data viz12401236Claude Opus 4.8
Design Arena: 3D12231244Gemini 3.5 Flash
Design Arena: all code categories12551266Gemini 3.5 Flash
Design Arena: SVG11941254Gemini 3.5 Flash
Design Arena: ASCII art12771254Claude Opus 4.8
LiveBench design78.8%Not measuredOnly Claude Opus 4.8 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index1122
General benchmarks for Claude Opus 4.8 and Gemini 3.5 Flash
BenchmarkClaude Opus 4.8Gemini 3.5 FlashLeader
LiveBench data analysis66.0%Not measuredOnly Claude Opus 4.8 measured
Public Benefits Bench (Vals AI)68.1%59.5%Claude Opus 4.8
SAGE (Vals AI)54.8%49.9%Claude Opus 4.8
MedScribe (Vals AI)85.8%76.6%Claude Opus 4.8
Vals Multimodal Index70.9%62.9%Claude Opus 4.8
IFBench62.2%76.3%Gemini 3.5 Flash
Long context reasoning (AA-LCR)77.7%74.3%Claude Opus 4.8
DTBench94.9%94.7%Claude Opus 4.8
LMCA57.5%47.1%Claude Opus 4.8
Surface Evolver Bench87.5%58.1%Claude Opus 4.8
Furniture assembly42.5%Not measuredOnly Claude Opus 4.8 measured
LMArena Text14611482Gemini 3.5 Flash
LMArena Text: instruction following14761467Claude Opus 4.8
LMArena Text: creative writing14541470Gemini 3.5 Flash
LMArena Vision12941308Gemini 3.5 Flash
LMArena Text: English14681481Gemini 3.5 Flash
LMArena Text: non-English14501475Gemini 3.5 Flash
LMArena Text: Chinese15061527Gemini 3.5 Flash
LMArena Text: German14721494Gemini 3.5 Flash
LMArena Text: Japanese14421486Gemini 3.5 Flash
LMArena Text: Korean14311448Gemini 3.5 Flash
LMArena Text: French14811490Gemini 3.5 Flash
LMArena Text: Spanish14651480Gemini 3.5 Flash
LMArena Text: Russian14741493Gemini 3.5 Flash
LMArena Text: Polish14591516Gemini 3.5 Flash
LMArena Text: multi-turn14761481Gemini 3.5 Flash
LMArena Text: longer queries14831483Claude Opus 4.8
LMArena Text: writing and language14611478Gemini 3.5 Flash
LMArena Text: entertainment and media14401459Gemini 3.5 Flash
LMArena Vision: English12931305Gemini 3.5 Flash
LMArena Vision: Chinese13461377Gemini 3.5 Flash
LMArena Vision: reading text13031317Gemini 3.5 Flash
LMArena Vision: humor12821321Gemini 3.5 Flash
LMArena Vision: creative writing13011301Gemini 3.5 Flash
LMArena Document14751463Claude Opus 4.8
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 4.8 and Gemini 3.5 Flash
BenchmarkClaude Opus 4.8Gemini 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 4.8$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 4.8$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 4.8$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 4.8 and Gemini 3.5 Flash
SpecificationAnthropic Claude Opus 4.8Google Gemini 3.5 Flash
MakerAnthropicGoogle
WeightsNo public weights listedNo public weights listed
ReleasedMay 27, 2026May 19, 2026
Context window1M1.05M
Input $/Mtok$5.00$1.50
Output $/Mtok$25.00$9.00
Coding index65.039.8
Independent measurements behind it64
Cost per solved task$2.17$1.21
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.8 better than Gemini 3.5 Flash for coding?

Pick Claude Opus 4.8 for coding: it scores 65.0 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 $2.17).

Which is cheaper, Claude Opus 4.8 or Gemini 3.5 Flash?

Claude Opus 4.8 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 4.8 costs $2.17 and Gemini 3.5 Flash $1.21.

Which has the bigger context window, Claude Opus 4.8 or Gemini 3.5 Flash?

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

How many benchmarks is the Claude Opus 4.8 vs Gemini 3.5 Flash comparison based on?

110 benchmarks have a result for both models as of October 21, 2026. Claude Opus 4.8'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-4-8-vs-gemini-3-5-flash" title="Claude Opus 4.8 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-4-8-vs-gemini-3-5-flash">LLMBenchmark.ai, Claude Opus 4.8 vs Gemini 3.5 Flash</a></p>