LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Opus 4.6 vs Gemini 3.8 Flash

Updated October 21, 2026. 87 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Opus 4.6 Replace Gemini 3.8 Flash
Claude Opus 4.6Anthropic
Coding
66.9
Overall
31.9
Output $/M
$25.00
33
Gemini 3.8 FlashGoogle
Coding
70.5
Overall
40.9
Output $/M
$4.125
54
vs boards won of 87 shared

Decision reading

Pick Gemini 3.8 Flash for coding: it scores 70.5 on the Vibe Coding Index against 66.9 for Claude Opus 4.6.

Pick Claude Opus 4.6 when a solved task costs $1.56 against $2.74, or when what matters is LMArena Text: coding or LMArena Text: software and IT, where it leads.

Model AClaude Opus 4.6Anthropic66.9/1002 independent benchmarks$1.56 per solved taskModel BGemini 3.8 FlashGoogle70.5/1002 independent benchmarks$2.74 per solved task
Shared results
87
Claude Opus 4.6 only
21
Gemini 3.8 Flash only
39
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 4.6 66.9 from 2 benchmarks, Gemini 3.8 Flash 70.5 from 2 benchmarks.
Widest category
Agentic work, 9.2 points apart on average over 7 shared benchmarks.
Widest single gap
Chess puzzles: Claude Opus 4.6 21.0% against Gemini 3.8 Flash 58.0%, 37.0 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.6 $25.00 against Gemini 3.8 Flash $4.125 per million output tokens, 6.1x apart.
Context window
Claude Opus 4.6 takes 1M tokens, Gemini 3.8 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 4.6BarsGemini 3.8 FlashTies
Coding29
Intelligence02
Agentic work25
Reasoning311
Math33
Knowledge55
Web design17
General1712
All shared boards3354
CodingLike-for-likeFour of these boards feed the Vibe Coding Index29
Coding benchmarks for Claude Opus 4.6 and Gemini 3.8 Flash
BenchmarkClaude Opus 4.6Gemini 3.8 FlashLeader
SWE-bench Verified75.6%Not measuredOnly Claude Opus 4.6 measured
SWE-bench Multilingual72.0%Not measuredOnly Claude Opus 4.6 measured
LiveBench codingNot measured82.2%Only Gemini 3.8 Flash measured
LMArena WebDev15471585Gemini 3.8 Flash
AA Coding IndexNot measured76.3Only Gemini 3.8 Flash measured
LiveCodeBench (Vals AI)84.7%89.5%Gemini 3.8 Flash
SWE-bench Verified (Vals AI)78.2%80.0%Gemini 3.8 Flash
Terminal-Bench 4 (Vals AI)Not measured19.7%Only Gemini 3.8 Flash measured
Vibe Code Bench (Vals AI)57.6%78.7%Gemini 3.8 Flash
Code migration (Vals AI)Not measured36.5%Only Gemini 3.8 Flash measured
ProgramBench (Vals AI)Not measured1.0%Only Gemini 3.8 Flash measured
IOI (Vals AI)Not measured56.9%Only Gemini 3.8 Flash measured
Terminal-Bench 2.1 (Vals AI)Not measured81.3%Only Gemini 3.8 Flash measured
SWE-bench Multimodal (Vals AI)Not measured40.8%Only Gemini 3.8 Flash measured
Vibe Code Bench 1-100 (Vals AI)Not measured18.8%Only Gemini 3.8 Flash measured
SkillsBench (Vals AI)Not measured58.0%Only Gemini 3.8 Flash measured
CyberBench (Vals AI)Not measured43.8%Only Gemini 3.8 Flash measured
SciCodeNot measured56.6%Only Gemini 3.8 Flash measured
Terminal-Bench Hard (Artificial Analysis run)48.5%Not measuredOnly Claude Opus 4.6 measured
Terminal-Bench79.8%Not measuredOnly Claude Opus 4.6 measured
FrontierCode26.6%41.2%Gemini 3.8 Flash
FrontierSWENot measured19.6%Only Gemini 3.8 Flash measured
GSO-Bench41.2%Not measuredOnly Claude Opus 4.6 measured
WeirdML78.0%84.8%Gemini 3.8 Flash
Cybench93.0%Not measuredOnly Claude Opus 4.6 measured
ALE-BenchNot measured1269.7Only Gemini 3.8 Flash measured
LMArena Text: coding15341508Claude Opus 4.6
LMArena Text: software and IT15271507Claude Opus 4.6
LMArena WebDev: React15391577Gemini 3.8 Flash
LMArena WebDev: HTML15591616Gemini 3.8 Flash
LMArena WebDev: from an image15431593Gemini 3.8 Flash
Neither model has a result on the other 7 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Opus 4.6 and Gemini 3.8 Flash
BenchmarkClaude Opus 4.6Gemini 3.8 FlashLeader
AA Intelligence Index31.940.9Gemini 3.8 Flash
Epoch Capabilities Index155.7157.4Gemini 3.8 Flash
Agentic workLike-for-likePublic boards, shown as published, kept out of the index25
Agentic work benchmarks for Claude Opus 4.6 and Gemini 3.8 Flash
BenchmarkClaude Opus 4.6Gemini 3.8 FlashLeader
AA Agentic IndexNot measured40.2Only Gemini 3.8 Flash measured
Design Arena: agents building web apps12061238Gemini 3.8 Flash
Design Arena: agents building full-stack apps12201244Gemini 3.8 Flash
Design Arena: agents building mobile apps12071236Gemini 3.8 Flash
Design Arena: agents building Android apps12041078Claude Opus 4.6
Design Arena: agents building Godot gamesNot measured1273Only Gemini 3.8 Flash measured
Design Arena: agents building games1214Not measuredOnly Claude Opus 4.6 measured
Design Arena: PowerPoint slidesNot measured1178Only Gemini 3.8 Flash measured
Design Arena: spreadsheetsNot measured1052Only Gemini 3.8 Flash measured
LiveBench researchNot measured79.1%Only Gemini 3.8 Flash measured
LiveBench browserNot measured64.0%Only Gemini 3.8 Flash measured
LiveBench long agenticNot measured30.1%Only Gemini 3.8 Flash measured
SREBench (Vals AI)Not measured11.1%Only Gemini 3.8 Flash measured
Finance Agent (Vals AI)Not measured61.4%Only Gemini 3.8 Flash measured
Tax Agent Bench (Vals AI)Not measured32.1%Only Gemini 3.8 Flash measured
Legal Research Bench (Vals AI)Not measured38.9%Only Gemini 3.8 Flash measured
Harvey's Legal Agent Benchmark (Vals AI)Not measured12.1%Only Gemini 3.8 Flash measured
Excel Modeling Benchmark (Vals AI)Not measured72.2%Only Gemini 3.8 Flash measured
BioMysteryBench (Vals AI)Not measured62.2%Only Gemini 3.8 Flash measured
Terminal-Bench-Science (Vals AI)Not measured8.6%Only Gemini 3.8 Flash measured
Vals Science IndexNot measured35.8%Only Gemini 3.8 Flash measured
Time Horizon Index (Vals AI)Not measured18.8%Only Gemini 3.8 Flash measured
CUA-bench (Vals AI)Not measured4.2%Only Gemini 3.8 Flash measured
τ²-Bench Telecom92.1%Not measuredOnly Claude Opus 4.6 measured
APEX-Agents46.3%64.3%Gemini 3.8 Flash
METR time horizons78.9%Not measuredOnly Claude Opus 4.6 measured
Remote Labor Index4.2%5.8%Gemini 3.8 Flash
DeepResearch Bench55.3%Not measuredOnly Claude Opus 4.6 measured
Vending-Bench 2$8,018$5,094Claude Opus 4.6
Neither model has a result on the other 10 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index311
Reasoning benchmarks for Claude Opus 4.6 and Gemini 3.8 Flash
BenchmarkClaude Opus 4.6Gemini 3.8 FlashLeader
GPQA Diamond89.7%94.4%Gemini 3.8 Flash
LiveBench reasoningNot measured89.3%Only Gemini 3.8 Flash measured
MysteryMechanism (Vals AI)Not measured36.5%Only Gemini 3.8 Flash measured
MMMU Pro (Vals AI)83.9%89.1%Gemini 3.8 Flash
GPQA Diamond (Artificial Analysis run)89.6%95.3%Gemini 3.8 Flash
Humanity's Last Exam (Artificial Analysis run)39.9%47.8%Gemini 3.8 Flash
GPQA Diamond (Epoch AI run)90.5%95.4%Gemini 3.8 Flash
ARC-AGI94.0%98.5%Gemini 3.8 Flash
ARC-AGI-269.2%89.2%Gemini 3.8 Flash
SimpleBench67.6%Not measuredOnly Claude Opus 4.6 measured
Chess puzzles21.0%58.0%Gemini 3.8 Flash
Mystery game puzzles25.0%47.0%Gemini 3.8 Flash
EBR-bench12.7%Not measuredOnly Claude Opus 4.6 measured
LMArena Text: hard prompts15251509Claude Opus 4.6
LMArena Text: expert15441526Claude Opus 4.6
LMArena Text: hard prompts in English15301504Claude Opus 4.6
LMArena Vision: diagrams13401345Gemini 3.8 Flash
LMArena Vision: homework13371351Gemini 3.8 Flash
Neither model has a result on the other 3 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index33
Math benchmarks for Claude Opus 4.6 and Gemini 3.8 Flash
BenchmarkClaude Opus 4.6Gemini 3.8 FlashLeader
AIME95.6%Not measuredOnly Claude Opus 4.6 measured
OTIS Mock AIME94.4%98.9%Gemini 3.8 Flash
FrontierMath, tiers 1 to 366.0%68.4%Gemini 3.8 Flash
FrontierMath, tier 426.8%22.0%Claude Opus 4.6
ProofBench50.0%48.0%Claude Opus 4.6
LMArena Text: math15181532Gemini 3.8 Flash
LMArena Text: mathematical work15251519Claude Opus 4.6
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index55
Knowledge benchmarks for Claude Opus 4.6 and Gemini 3.8 Flash
BenchmarkClaude Opus 4.6Gemini 3.8 FlashLeader
MMLU Pro89.1%90.2%Gemini 3.8 Flash
LegalBench (Vals AI)85.3%87.0%Gemini 3.8 Flash
CaseLaw (Vals AI)62.1%Not measuredOnly Claude Opus 4.6 measured
CorpFin (Vals AI)67.0%Not measuredOnly Claude Opus 4.6 measured
TaxEval (Vals AI)76.0%74.5%Claude Opus 4.6
MortgageTax (Vals AI)68.5%65.3%Claude Opus 4.6
MedQA (Vals AI)95.4%Not measuredOnly Claude Opus 4.6 measured
MedCode (Vals AI)49.1%48.1%Claude Opus 4.6
SimpleQA Verified47.0%69.7%Gemini 3.8 Flash
LMArena Text: science15191523Gemini 3.8 Flash
LMArena Text: medicine and healthcare15041508Gemini 3.8 Flash
LMArena Text: legal and government15121497Claude Opus 4.6
LMArena Text: business and finance14971479Claude Opus 4.6
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index17
Web design benchmarks for Claude Opus 4.6 and Gemini 3.8 Flash
BenchmarkClaude Opus 4.6Gemini 3.8 FlashLeader
Design Arena: websites12911301Gemini 3.8 Flash
Design Arena: UI components12841318Gemini 3.8 Flash
Design Arena: game dev12781305Gemini 3.8 Flash
Design Arena: data viz12791269Claude Opus 4.6
Design Arena: 3D12741295Gemini 3.8 Flash
Design Arena: all code categories12891304Gemini 3.8 Flash
Design Arena: SVG12271295Gemini 3.8 Flash
Design Arena: ASCII art12541264Gemini 3.8 Flash
LiveBench designNot measured72.7%Only Gemini 3.8 Flash measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index1712
General benchmarks for Claude Opus 4.6 and Gemini 3.8 Flash
BenchmarkClaude Opus 4.6Gemini 3.8 FlashLeader
Vals IndexNot measured56.0%Only Gemini 3.8 Flash measured
LiveBench data analysisNot measured54.0%Only Gemini 3.8 Flash measured
Public Benefits Bench (Vals AI)Not measured65.3%Only Gemini 3.8 Flash measured
SAGE (Vals AI)51.6%35.1%Claude Opus 4.6
MedScribe (Vals AI)86.7%84.5%Claude Opus 4.6
IFBench53.1%Not measuredOnly Claude Opus 4.6 measured
Long context reasoning (AA-LCR)78.0%84.0%Gemini 3.8 Flash
DTBench91.2%95.7%Gemini 3.8 Flash
LMCA55.8%52.9%Claude Opus 4.6
CL-bench20.7%Not measuredOnly Claude Opus 4.6 measured
Surface Evolver BenchNot measured76.9%Only Gemini 3.8 Flash measured
Furniture assembly28.3%31.7%Gemini 3.8 Flash
CL-bench Life17.0%Not measuredOnly Claude Opus 4.6 measured
LMArena Text15011499Claude Opus 4.6
LMArena Text: instruction following15211492Claude Opus 4.6
LMArena Text: creative writing15051488Claude Opus 4.6
LMArena Vision13161315Claude Opus 4.6
LMArena Text: English15111498Claude Opus 4.6
LMArena Text: non-English14881491Gemini 3.8 Flash
LMArena Text: Chinese15511553Gemini 3.8 Flash
LMArena Text: German15001501Gemini 3.8 Flash
LMArena Text: Japanese14881507Gemini 3.8 Flash
LMArena Text: Korean14641464Gemini 3.8 Flash
LMArena Text: French15121496Claude Opus 4.6
LMArena Text: Spanish15101487Claude Opus 4.6
LMArena Text: Russian14971514Gemini 3.8 Flash
LMArena Text: Polish14991497Claude Opus 4.6
LMArena Text: multi-turn15111503Claude Opus 4.6
LMArena Text: longer queries15181507Claude Opus 4.6
LMArena Text: writing and language15021494Claude Opus 4.6
LMArena Text: entertainment and media14921480Claude Opus 4.6
LMArena Vision: English13241318Claude Opus 4.6
LMArena Vision: Chinese13701416Gemini 3.8 Flash
LMArena Vision: reading text13261333Gemini 3.8 Flash
LMArena Vision: humor13141321Gemini 3.8 Flash
LMArena Vision: recognizing things1274Not measuredOnly Claude Opus 4.6 measured
LMArena Vision: creative writing13311299Claude Opus 4.6
LMArena Document1507Not measuredOnly Claude Opus 4.6 measured
Neither model has a result on the other 8 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Opus 4.6 and Gemini 3.8 Flash
BenchmarkClaude Opus 4.6Gemini 3.8 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 4.6$0.018Fits in one request
Gemini 3.8 Flash$0.0029Fits in one request

Gemini 3.8 Flash costs less

Repository review

50K input + 3K output tokens

Claude Opus 4.6$0.325Fits in one request
Gemini 3.8 Flash$0.054Fits in one request

Gemini 3.8 Flash costs less

Agent loop

200K input + 10K output tokens

Claude Opus 4.6$1.25Fits in one request
Gemini 3.8 Flash$0.206Fits in one request

Gemini 3.8 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 4.6 and Gemini 3.8 Flash
SpecificationAnthropic Claude Opus 4.6Google Gemini 3.8 Flash
MakerAnthropicGoogle
WeightsNo public weights listedNo public weights listed
ReleasedFebruary 4, 2026September 2, 2026
Context window1M1.05M
Input $/Mtok$5.00$0.825
Output $/Mtok$25.00$4.125
Coding index66.970.5
Independent measurements behind it22
Cost per solved task$1.56$2.74
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.6 better than Gemini 3.8 Flash for coding?

Pick Gemini 3.8 Flash for coding: it scores 70.5 on the Vibe Coding Index against 66.9 for Claude Opus 4.6. Pick Claude Opus 4.6 when a solved task costs $1.56 against $2.74, or when what matters is LMArena Text: coding or LMArena Text: software and IT, where it leads.

Which is cheaper, Claude Opus 4.6 or Gemini 3.8 Flash?

Claude Opus 4.6 costs $5.00 per million input tokens and $25.00 per million output tokens; Gemini 3.8 Flash costs $0.825 and $4.125. Per solved SWE-bench Verified task, Claude Opus 4.6 costs $1.56 and Gemini 3.8 Flash $2.74.

Which has the bigger context window, Claude Opus 4.6 or Gemini 3.8 Flash?

Gemini 3.8 Flash, with 1.05M tokens against 1M.

How many benchmarks is the Claude Opus 4.6 vs Gemini 3.8 Flash comparison based on?

87 benchmarks have a result for both models as of October 21, 2026. Claude Opus 4.6's coding index rests on 2 independent benchmarks and Gemini 3.8 Flash's on 2. 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-4-6-vs-gemini-3-8-flash" title="Claude Opus 4.6 vs Gemini 3.8 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-4-6-vs-gemini-3-8-flash">LLMBenchmark.ai, Claude Opus 4.6 vs Gemini 3.8 Flash</a></p>