LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Opus 4.8 vs Gemini 3.6 Flash

Updated October 21, 2026. 101 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Opus 4.8 Replace Gemini 3.6 Flash
Claude Opus 4.8Anthropic
Coding
66.0
Overall
41.8
Output $/M
$25.00
55
Gemini 3.6 FlashGoogle
Coding
48.3
Overall
34.0
Output $/M
$3.75
45
vs boards won of 101 shared, 1 tied

Decision reading

Pick Claude Opus 4.8 for coding: it scores 66.0 on the Vibe Coding Index against 48.3 for Gemini 3.6 Flash.

Pick Gemini 3.6 Flash when output tokens cost 6.7x less, or when a solved task costs $1.49 against $2.17.

Model AClaude Opus 4.8Anthropic66.0/1002 independent benchmarks$2.17 per solved taskModel BGemini 3.6 FlashGoogle48.3/1001 independent benchmark$1.49 per solved task
Shared results
101
Claude Opus 4.8 only
25
Gemini 3.6 Flash only
6
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
Claude Opus 4.8 66.0 from 2 benchmarks, Gemini 3.6 Flash 48.3 from 1 benchmark.
Widest category
Math, 16.1 points apart on average over 6 shared benchmarks.
Widest single gap
FrontierMath, tier 4: Claude Opus 4.8 56.1% against Gemini 3.6 Flash 22.0%, 34.1 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.8 $25.00 against Gemini 3.6 Flash $3.75 per million output tokens, 6.7x apart.
Context window
Claude Opus 4.8 takes 1M tokens, Gemini 3.6 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 3.6 FlashTies
Coding105
Intelligence20
Agentic work1211 tie
Reasoning95
Math51
Knowledge56
Web design16
General1121
All shared boards55451 tie
CodingLike-for-likeFour of these boards feed the Vibe Coding Index105
Coding benchmarks for Claude Opus 4.8 and Gemini 3.6 Flash
BenchmarkClaude Opus 4.8Gemini 3.6 FlashLeader
LiveBench coding77.3%Not measuredOnly Claude Opus 4.8 measured
LMArena WebDev15561538Claude Opus 4.8
AA Coding Index74.369.2Claude Opus 4.8
LiveCodeBench (Vals AI)87.8%88.1%Gemini 3.6 Flash
SWE-bench Verified (Vals AI)88.6%79.6%Claude Opus 4.8
Terminal-Bench 4 (Vals AI)23.2%Not measuredOnly Claude Opus 4.8 measured
Vibe Code Bench (Vals AI)82.7%64.0%Claude Opus 4.8
Code migration (Vals AI)47.3%30.9%Claude Opus 4.8
ProgramBench (Vals AI)1.0%0.0%Claude Opus 4.8
IOI (Vals AI)Not measured35.1%Only Gemini 3.6 Flash measured
Terminal-Bench 2.1 (Vals AI)71.9%73.8%Gemini 3.6 Flash
SkillsBench (Vals AI)59.2%Not measuredOnly Claude Opus 4.8 measured
CyberBench (Vals AI)Not measured45.4%Only Gemini 3.6 Flash measured
SciCode54.4%53.4%Claude Opus 4.8
Terminal-Bench Hard (Artificial Analysis run)58.3%Not measuredOnly Claude Opus 4.8 measured
FrontierCode46.5%34.4%Claude Opus 4.8
GSO-Bench47.1%Not measuredOnly Claude Opus 4.8 measured
WeirdML82.9%56.1%Claude Opus 4.8
ALE-BenchNot measured715.5Only Gemini 3.6 Flash measured
LMArena Text: coding14901491Gemini 3.6 Flash
LMArena Text: software and IT14881492Gemini 3.6 Flash
LMArena WebDev: React15571528Claude Opus 4.8
LMArena WebDev: HTML15431547Gemini 3.6 Flash
LMArena WebDev: from an imageNot measured1545Only Gemini 3.6 Flash measured
Neither model has a result on the other 14 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Opus 4.8 and Gemini 3.6 Flash
BenchmarkClaude Opus 4.8Gemini 3.6 FlashLeader
AA Intelligence Index41.834.0Claude Opus 4.8
Epoch Capabilities Index159.0154.5Claude Opus 4.8
Agentic workLike-for-likePublic boards, shown as published, kept out of the index121
Agentic work benchmarks for Claude Opus 4.8 and Gemini 3.6 Flash
BenchmarkClaude Opus 4.8Gemini 3.6 FlashLeader
AA Agentic Index41.929.0Claude Opus 4.8
Design Arena: agents building web apps12331197Claude Opus 4.8
Design Arena: agents building full-stack apps12491181Claude Opus 4.8
Design Arena: agents building mobile apps12221199Claude Opus 4.8
Design Arena: agents building Android apps12371208Claude Opus 4.8
Design Arena: agents building Godot games1231Not measuredOnly Claude Opus 4.8 measured
Design Arena: agents building games12381181Claude Opus 4.8
Design Arena: HTML slides12211148Claude Opus 4.8
Design Arena: PowerPoint slides12271146Claude Opus 4.8
Design Arena: spreadsheetsNot measured1017Only Gemini 3.6 Flash 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%56.3%Gemini 3.6 Flash
Tax Agent Bench (Vals AI)30.0%18.0%Claude Opus 4.8
Legal Research Bench (Vals AI)43.8%25.0%Claude Opus 4.8
Excel Modeling Benchmark (Vals AI)69.4%65.4%Claude Opus 4.8
BioMysteryBench (Vals AI)Not measured58.5%Only Gemini 3.6 Flash measured
Terminal-Bench-Science (Vals AI)4.3%4.3%Tie
Time Horizon Index (Vals AI)11.8%Not measuredOnly Claude Opus 4.8 measured
τ²-Bench Telecom94.4%Not measuredOnly Claude Opus 4.8 measured
APEX-Agents48.9%46.9%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$5,787Not measuredOnly Claude Opus 4.8 measured
LMArena Search1204Not measuredOnly Claude Opus 4.8 measured
Neither model has a result on the other 11 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index95
Reasoning benchmarks for Claude Opus 4.8 and Gemini 3.6 Flash
BenchmarkClaude Opus 4.8Gemini 3.6 FlashLeader
GPQA Diamond92.4%93.4%Gemini 3.6 Flash
LiveBench reasoning89.2%Not measuredOnly Claude Opus 4.8 measured
MMMU Pro (Vals AI)86.6%88.4%Gemini 3.6 Flash
GPQA Diamond (Artificial Analysis run)92.0%92.8%Gemini 3.6 Flash
Humanity's Last Exam (Artificial Analysis run)48.7%40.8%Claude Opus 4.8
GPQA Diamond (Epoch AI run)91.0%94.1%Gemini 3.6 Flash
ARC-AGI92.5%91.2%Claude Opus 4.8
ARC-AGI-272.1%60.4%Claude Opus 4.8
SimpleBench64.8%Not measuredOnly Claude Opus 4.8 measured
Chess puzzles52.0%42.0%Claude Opus 4.8
Mystery game puzzles36.0%30.0%Claude Opus 4.8
EBR-bench28.6%Not measuredOnly Claude Opus 4.8 measured
LMArena Text: hard prompts14821486Gemini 3.6 Flash
LMArena Text: expert15031490Claude Opus 4.8
LMArena Text: hard prompts in English14871484Claude Opus 4.8
LMArena Vision: diagrams13151314Claude Opus 4.8
LMArena Vision: homework13371314Claude Opus 4.8
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 3.6 Flash
BenchmarkClaude Opus 4.8Gemini 3.6 FlashLeader
OTIS Mock AIME98.3%94.2%Claude Opus 4.8
FrontierMath, tiers 1 to 380.0%58.9%Claude Opus 4.8
FrontierMath, tier 456.1%22.0%Claude Opus 4.8
ProofBench69.0%36.0%Claude Opus 4.8
LMArena Text: math14861508Gemini 3.6 Flash
LMArena Text: mathematical work14971492Claude 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 index56
Knowledge benchmarks for Claude Opus 4.8 and Gemini 3.6 Flash
BenchmarkClaude Opus 4.8Gemini 3.6 FlashLeader
MMLU Pro89.6%89.3%Claude Opus 4.8
LegalBench (Vals AI)83.6%86.7%Gemini 3.6 Flash
CorpFin (Vals AI)66.7%63.3%Claude Opus 4.8
TaxEval (Vals AI)75.6%74.9%Claude Opus 4.8
MortgageTax (Vals AI)69.9%67.6%Claude Opus 4.8
MedCode (Vals AI)53.2%53.1%Claude Opus 4.8
SimpleQA Verified53.0%66.2%Gemini 3.6 Flash
LMArena Text: science14771489Gemini 3.6 Flash
LMArena Text: medicine and healthcare14641469Gemini 3.6 Flash
LMArena Text: legal and government14771479Gemini 3.6 Flash
LMArena Text: business and finance14581464Gemini 3.6 Flash
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index16
Web design benchmarks for Claude Opus 4.8 and Gemini 3.6 Flash
BenchmarkClaude Opus 4.8Gemini 3.6 FlashLeader
Design Arena: websites12581301Gemini 3.6 Flash
Design Arena: UI components12561297Gemini 3.6 Flash
Design Arena: game dev12641263Claude Opus 4.8
Design Arena: data viz12401289Gemini 3.6 Flash
Design Arena: 3D12231272Gemini 3.6 Flash
Design Arena: all code categories12551290Gemini 3.6 Flash
Design Arena: SVG1194Not measuredOnly Claude Opus 4.8 measured
Design Arena: ASCII art12761281Gemini 3.6 Flash
LiveBench design78.8%Not measuredOnly Claude Opus 4.8 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index1121
General benchmarks for Claude Opus 4.8 and Gemini 3.6 Flash
BenchmarkClaude Opus 4.8Gemini 3.6 FlashLeader
LiveBench data analysis66.0%Not measuredOnly Claude Opus 4.8 measured
Public Benefits Bench (Vals AI)68.1%56.6%Claude Opus 4.8
SAGE (Vals AI)54.8%48.7%Claude Opus 4.8
MedScribe (Vals AI)85.8%79.7%Claude Opus 4.8
Vals Multimodal Index70.9%65.1%Claude Opus 4.8
IFBench62.2%Not measuredOnly Claude Opus 4.8 measured
Long context reasoning (AA-LCR)77.7%80.0%Gemini 3.6 Flash
DTBench94.9%95.5%Gemini 3.6 Flash
LMCA57.5%44.9%Claude Opus 4.8
Surface Evolver Bench87.5%Not measuredOnly Claude Opus 4.8 measured
Furniture assembly42.5%23.3%Claude Opus 4.8
LMArena Text14611480Gemini 3.6 Flash
LMArena Text: instruction following14761467Claude Opus 4.8
LMArena Text: creative writing14541466Gemini 3.6 Flash
LMArena Vision12941299Gemini 3.6 Flash
LMArena Text: English14681482Gemini 3.6 Flash
LMArena Text: non-English14501470Gemini 3.6 Flash
LMArena Text: Chinese15061531Gemini 3.6 Flash
LMArena Text: German14721480Gemini 3.6 Flash
LMArena Text: Japanese14421475Gemini 3.6 Flash
LMArena Text: Korean14311429Claude Opus 4.8
LMArena Text: French14811503Gemini 3.6 Flash
LMArena Text: Spanish14651476Gemini 3.6 Flash
LMArena Text: Russian14741488Gemini 3.6 Flash
LMArena Text: Polish14591473Gemini 3.6 Flash
LMArena Text: multi-turn14761481Gemini 3.6 Flash
LMArena Text: longer queries14831475Claude Opus 4.8
LMArena Text: writing and language14611470Gemini 3.6 Flash
LMArena Text: entertainment and media14401456Gemini 3.6 Flash
LMArena Vision: English12931295Gemini 3.6 Flash
LMArena Vision: Chinese13461357Gemini 3.6 Flash
LMArena Vision: reading text13031312Gemini 3.6 Flash
LMArena Vision: humor12821289Gemini 3.6 Flash
LMArena Vision: creative writing13011278Claude Opus 4.8
LMArena Document14751456Claude 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 3.6 Flash
BenchmarkClaude Opus 4.8Gemini 3.6 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 3.6 Flash$0.0026Fits in one request

Gemini 3.6 Flash costs less

Repository review

50K input + 3K output tokens

Claude Opus 4.8$0.325Fits in one request
Gemini 3.6 Flash$0.049Fits in one request

Gemini 3.6 Flash costs less

Agent loop

200K input + 10K output tokens

Claude Opus 4.8$1.25Fits in one request
Gemini 3.6 Flash$0.188Fits in one request

Gemini 3.6 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 3.6 Flash
SpecificationAnthropic Claude Opus 4.8Google Gemini 3.6 Flash
MakerAnthropicGoogle
WeightsNo public weights listedNo public weights listed
ReleasedMay 27, 2026July 21, 2026
Context window1M1.05M
Input $/Mtok$5.00$0.75
Output $/Mtok$25.00$3.75
Coding index66.048.3
Independent measurements behind it21
Cost per solved task$2.17$1.49
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.8 better than Gemini 3.6 Flash for coding?

Pick Claude Opus 4.8 for coding: it scores 66.0 on the Vibe Coding Index against 48.3 for Gemini 3.6 Flash. Pick Gemini 3.6 Flash when output tokens cost 6.7x less, or when a solved task costs $1.49 against $2.17.

Which is cheaper, Claude Opus 4.8 or Gemini 3.6 Flash?

Claude Opus 4.8 costs $5.00 per million input tokens and $25.00 per million output tokens; Gemini 3.6 Flash costs $0.75 and $3.75. Per solved SWE-bench Verified task, Claude Opus 4.8 costs $2.17 and Gemini 3.6 Flash $1.49.

Which has the bigger context window, Claude Opus 4.8 or Gemini 3.6 Flash?

Gemini 3.6 Flash, with 1.05M tokens against 1M.

How many benchmarks is the Claude Opus 4.8 vs Gemini 3.6 Flash comparison based on?

101 benchmarks have a result for both models as of October 21, 2026. Claude Opus 4.8's coding index rests on 2 independent benchmarks and Gemini 3.6 Flash's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next