Enter opens the highlighted result. Esc closes.

Claude Opus 4.6 vs Claude Sonnet 4.6

Claude Sonnet 4.6 leads Claude Opus 4.6 on coding, 57.3 to 57.2 on the Vibe Coding Index, and Claude Sonnet 4.6 costs 1.7x less per output token ($15.00 vs $25.00 per million). Updated October 22, 2026; 94 benchmarks have a result for both.

Replace Claude Opus 4.6 Replace Claude Sonnet 4.6
Claude Opus 4.6Anthropic
Coding
57.2
Overall
66.0
Output $/M
$25.00
86
Claude Sonnet 4.6Anthropic
Coding
57.3
Overall
60.3
Output $/M
$15.00
7
vs boards won of 94 shared, 1 tied

Claude Opus 4.6 or Claude Sonnet 4.6: which to pick

Claude Opus 4.6 and Claude Sonnet 4.6 are level for coding, 57.2 against 57.3 on the Vibe Coding Index, so price and context decide.

Pick Claude Opus 4.6 for a lower cost per solved task ($1.56 against $1.68) and work measured by LMArena WebDev or LiveCodeBench (Vals AI), where it leads. Pick Claude Sonnet 4.6 for output tokens 1.7x cheaper ($15.00 vs $25.00 per million) and work measured by Terminal-Bench Hard (Artificial Analysis run) or Design Arena: agents building mobile apps, where it leads.

Model AClaude Opus 4.6Anthropic57.2/1004 independent benchmarks$1.56 per solved taskModel BClaude Sonnet 4.6Anthropic57.3/1005 independent benchmarks$1.68 per solved task
Shared results
94
Claude Opus 4.6 only
16
Claude Sonnet 4.6 only
24
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 4.6 57.2 from 4 benchmarks, Claude Sonnet 4.6 57.3 from 5 benchmarks.
Widest category
General, 7.9 points apart on average over 30 shared benchmarks.
Widest single gap
Terminal-Bench: Claude Opus 4.6 79.8% against Claude Sonnet 4.6 53.4%, 26.4 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.6 $25.00 against Claude Sonnet 4.6 $15.00 per million output tokens, 1.7x apart.
Context window
Both take 1M tokens.

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 4.6BarsClaude Sonnet 4.6Ties
Coding121
Intelligence20
Agentic work711 tie
Reasoning131
Math50
Knowledge112
Web design80
General282
All shared boards8671 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index121
Coding benchmarks for Claude Opus 4.6 and Claude Sonnet 4.6
BenchmarkClaude Opus 4.6Claude Sonnet 4.6Leader
SWE-bench Verified75.6%Not measuredOnly Claude Opus 4.6 measured
SWE-bench Multilingual72.0%Not measuredOnly Claude Opus 4.6 measured
LiveBench codingNot measured66.6%Only Claude Sonnet 4.6 measured
LMArena WebDev15471523Claude Opus 4.6
AA Coding IndexNot measured63.0Only Claude Sonnet 4.6 measured
LiveCodeBench (Vals AI)84.7%82.1%Claude Opus 4.6
SWE-bench Verified (Vals AI)78.2%77.4%Claude Opus 4.6
Vibe Code Bench (Vals AI)57.6%55.8%Claude Opus 4.6
Code migration (Vals AI)Not measured39.9%Only Claude Sonnet 4.6 measured
ProgramBench (Vals AI)Not measured0.5%Only Claude Sonnet 4.6 measured
Terminal-Bench 2.1 (Vals AI)Not measured57.3%Only Claude Sonnet 4.6 measured
SkillsBench (Vals AI)Not measured49.0%Only Claude Sonnet 4.6 measured
SciCodeNot measured50.1%Only Claude Sonnet 4.6 measured
Terminal-Bench Hard (Artificial Analysis run)48.5%53.0%Claude Sonnet 4.6
Terminal-Bench79.8%53.4%Claude Opus 4.6
FrontierCode26.6%24.3%Claude Opus 4.6
GSO-Bench41.2%Not measuredOnly Claude Opus 4.6 measured
WeirdML78.0%66.1%Claude Opus 4.6
Cybench93.0%Not measuredOnly Claude Opus 4.6 measured
LMArena Text: coding15341503Claude Opus 4.6
LMArena Text: software and IT15271491Claude Opus 4.6
LMArena WebDev: React15391512Claude Opus 4.6
LMArena WebDev: HTML15591527Claude Opus 4.6
LMArena WebDev: from an image15431529Claude Opus 4.6
Neither model has a result on the other 15 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Opus 4.6 and Claude Sonnet 4.6
BenchmarkClaude Opus 4.6Claude Sonnet 4.6Leader
AA Intelligence Index31.930.1Claude Opus 4.6
Epoch Capabilities Index155.7152.8Claude Opus 4.6
Agentic workLike-for-likePublic boards, shown as published, kept out of the index71
Agentic work benchmarks for Claude Opus 4.6 and Claude Sonnet 4.6
BenchmarkClaude Opus 4.6Claude Sonnet 4.6Leader
AA Agentic IndexNot measured31.8Only Claude Sonnet 4.6 measured
Design Arena: agents building web apps12061190Claude Opus 4.6
Design Arena: agents building full-stack apps12201213Claude Opus 4.6
Design Arena: agents building mobile apps12071212Claude Sonnet 4.6
Design Arena: agents building Android apps11971197Tie
Design Arena: agents building Godot gamesNot measured1226Only Claude Sonnet 4.6 measured
Design Arena: agents building games12121177Claude Opus 4.6
LiveBench researchNot measured63.6%Only Claude Sonnet 4.6 measured
LiveBench browserNot measured68.0%Only Claude Sonnet 4.6 measured
LiveBench long agenticNot measured23.1%Only Claude Sonnet 4.6 measured
Finance Agent (Vals AI)Not measured51.0%Only Claude Sonnet 4.6 measured
Tax Agent Bench (Vals AI)Not measured25.8%Only Claude Sonnet 4.6 measured
Legal Research Bench (Vals AI)Not measured38.5%Only Claude Sonnet 4.6 measured
Excel Modeling Benchmark (Vals AI)Not measured60.2%Only Claude Sonnet 4.6 measured
τ²-Bench Telecom92.1%79.5%Claude Opus 4.6
APEX-Agents46.3%43.0%Claude Opus 4.6
METR time horizons78.9%Not measuredOnly Claude Opus 4.6 measured
Remote Labor Index4.2%Not measuredOnly Claude Opus 4.6 measured
OSWorld 2.0Not measured9.3%Only Claude Sonnet 4.6 measured
DeepResearch Bench55.3%54.9%Claude Opus 4.6
OSWorldNot measured72.1%Only Claude Sonnet 4.6 measured
Vending-Bench 2$8,018$7,204Claude Opus 4.6
Neither model has a result on the other 19 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index131
Reasoning benchmarks for Claude Opus 4.6 and Claude Sonnet 4.6
BenchmarkClaude Opus 4.6Claude Sonnet 4.6Leader
GPQA Diamond89.7%85.6%Claude Opus 4.6
LiveBench reasoningNot measured86.4%Only Claude Sonnet 4.6 measured
MMMU Pro (Vals AI)83.9%83.6%Claude Opus 4.6
GPQA Diamond (Artificial Analysis run)89.6%87.5%Claude Opus 4.6
Humanity's Last Exam (Artificial Analysis run)39.9%33.6%Claude Opus 4.6
GPQA Diamond (Epoch AI run)90.5%87.4%Claude Opus 4.6
ARC-AGI94.0%86.5%Claude Opus 4.6
ARC-AGI-269.2%60.4%Claude Opus 4.6
SimpleBench67.6%Not measuredOnly Claude Opus 4.6 measured
Chess puzzles21.0%23.0%Claude Sonnet 4.6
Mystery game puzzles25.0%16.0%Claude Opus 4.6
EBR-bench12.7%Not measuredOnly Claude Opus 4.6 measured
LMArena Text: hard prompts15251485Claude Opus 4.6
LMArena Text: expert15441500Claude Opus 4.6
LMArena Text: hard prompts in English15301493Claude Opus 4.6
LMArena Vision: diagrams13401306Claude Opus 4.6
LMArena Vision: homework13371311Claude Opus 4.6
Kagi LLM Benchmark83.6%Not measuredOnly Claude Opus 4.6 measured
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index50
Math benchmarks for Claude Opus 4.6 and Claude Sonnet 4.6
BenchmarkClaude Opus 4.6Claude Sonnet 4.6Leader
AIME95.6%92.3%Claude Opus 4.6
OTIS Mock AIME94.4%85.8%Claude Opus 4.6
FrontierMath, tiers 1 to 366.0%Not measuredOnly Claude Opus 4.6 measured
FrontierMath, tier 426.8%Not measuredOnly Claude Opus 4.6 measured
ProofBench50.0%45.0%Claude Opus 4.6
LMArena Text: math15181462Claude Opus 4.6
LMArena Text: mathematical work15251483Claude 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 index112
Knowledge benchmarks for Claude Opus 4.6 and Claude Sonnet 4.6
BenchmarkClaude Opus 4.6Claude Sonnet 4.6Leader
MMLU Pro89.1%87.3%Claude Opus 4.6
LegalBench (Vals AI)85.3%82.1%Claude Opus 4.6
CaseLaw (Vals AI)62.1%64.0%Claude Sonnet 4.6
CorpFin (Vals AI)67.0%65.3%Claude Opus 4.6
TaxEval (Vals AI)76.0%77.1%Claude Sonnet 4.6
MortgageTax (Vals AI)68.5%67.7%Claude Opus 4.6
MedQA (Vals AI)95.4%92.1%Claude Opus 4.6
MedCode (Vals AI)49.1%Not measuredOnly Claude Opus 4.6 measured
SimpleQA Verified47.0%35.5%Claude Opus 4.6
LMArena Text: science15191474Claude Opus 4.6
LMArena Text: medicine and healthcare15041451Claude Opus 4.6
LMArena Text: legal and government15121470Claude Opus 4.6
LMArena Text: business and finance14971464Claude Opus 4.6
FACTS Benchmark Suite41.5%37.0%Claude 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 index80
Web design benchmarks for Claude Opus 4.6 and Claude Sonnet 4.6
BenchmarkClaude Opus 4.6Claude Sonnet 4.6Leader
Design Arena: websites12911284Claude Opus 4.6
Design Arena: UI components12811269Claude Opus 4.6
Design Arena: game dev12771258Claude Opus 4.6
Design Arena: data viz12791278Claude Opus 4.6
Design Arena: 3D12731234Claude Opus 4.6
Design Arena: all code categories12881275Claude Opus 4.6
Design Arena: SVG12271196Claude Opus 4.6
Design Arena: ASCII art12551235Claude Opus 4.6
LiveBench designNot measured71.8%Only Claude Sonnet 4.6 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index282
General benchmarks for Claude Opus 4.6 and Claude Sonnet 4.6
BenchmarkClaude Opus 4.6Claude Sonnet 4.6Leader
LiveBench data analysisNot measured76.1%Only Claude Sonnet 4.6 measured
Public Benefits Bench (Vals AI)Not measured62.5%Only Claude Sonnet 4.6 measured
SAGE (Vals AI)51.6%46.6%Claude Opus 4.6
MedScribe (Vals AI)86.7%Not measuredOnly Claude Opus 4.6 measured
Vals Multimodal IndexNot measured60.6%Only Claude Sonnet 4.6 measured
IFBench53.1%56.6%Claude Sonnet 4.6
Long context reasoning (AA-LCR)78.0%80.0%Claude Sonnet 4.6
DTBench91.2%89.9%Claude Opus 4.6
LMCA55.8%46.5%Claude Opus 4.6
CL-bench20.7%Not measuredOnly Claude Opus 4.6 measured
Furniture assembly28.3%Not measuredOnly Claude Opus 4.6 measured
ExploitBenchNot measured23.6%Only Claude Sonnet 4.6 measured
CL-bench Life17.0%Not measuredOnly Claude Opus 4.6 measured
LMArena Text15011458Claude Opus 4.6
LMArena Text: instruction following15211476Claude Opus 4.6
LMArena Text: creative writing15051435Claude Opus 4.6
LMArena Vision13161283Claude Opus 4.6
LMArena Text: English15111472Claude Opus 4.6
LMArena Text: non-English14881440Claude Opus 4.6
LMArena Text: Chinese15511491Claude Opus 4.6
LMArena Text: German15001428Claude Opus 4.6
LMArena Text: Japanese14881420Claude Opus 4.6
LMArena Text: Korean14641410Claude Opus 4.6
LMArena Text: French15121465Claude Opus 4.6
LMArena Text: Spanish15101464Claude Opus 4.6
LMArena Text: Russian14971440Claude Opus 4.6
LMArena Text: Polish14991443Claude Opus 4.6
LMArena Text: multi-turn15111464Claude Opus 4.6
LMArena Text: longer queries15181479Claude Opus 4.6
LMArena Text: writing and language15021444Claude Opus 4.6
LMArena Text: entertainment and media14921431Claude Opus 4.6
LMArena Vision: English13241298Claude Opus 4.6
LMArena Vision: Chinese13701307Claude Opus 4.6
LMArena Vision: reading text13261296Claude Opus 4.6
LMArena Vision: humor13141248Claude Opus 4.6
LMArena Vision: recognizing things12741195Claude Opus 4.6
LMArena Vision: creative writing13311272Claude Opus 4.6
LMArena Document15071482Claude Opus 4.6
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 Claude Sonnet 4.6
BenchmarkClaude Opus 4.6Claude Sonnet 4.6Leader
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
Claude Sonnet 4.6$0.011Fits in one request

Claude Sonnet 4.6 costs less

Repository review

50K input + 3K output tokens

Claude Opus 4.6$0.325Fits in one request
Claude Sonnet 4.6$0.195Fits in one request

Claude Sonnet 4.6 costs less

Agent loop

200K input + 10K output tokens

Claude Opus 4.6$1.25Fits in one request
Claude Sonnet 4.6$0.750Fits in one request

Claude Sonnet 4.6 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 Claude Sonnet 4.6
SpecificationAnthropic Claude Opus 4.6Anthropic Claude Sonnet 4.6
MakerAnthropicAnthropic
WeightsNo public weights listedNo public weights listed
ReleasedFebruary 4, 2026February 17, 2026
Context window1M1M
Input $/Mtok$5.00$3.00
Output $/Mtok$25.00$15.00
Coding index57.257.3
Independent measurements behind it45
Cost per solved task$1.56$1.68
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.6 better than Claude Sonnet 4.6 for coding?

Claude Opus 4.6 and Claude Sonnet 4.6 are level for coding, 57.2 against 57.3 on the Vibe Coding Index, so price and context decide. Pick Claude Opus 4.6 for a lower cost per solved task ($1.56 against $1.68) and work measured by LMArena WebDev or LiveCodeBench (Vals AI), where it leads. Pick Claude Sonnet 4.6 for output tokens 1.7x cheaper ($15.00 vs $25.00 per million) and work measured by Terminal-Bench Hard (Artificial Analysis run) or Design Arena: agents building mobile apps, where it leads.

Which is cheaper, Claude Opus 4.6 or Claude Sonnet 4.6?

Claude Opus 4.6 costs $5.00 per million input tokens and $25.00 per million output tokens; Claude Sonnet 4.6 costs $3.00 and $15.00. Per solved SWE-bench Verified task, Claude Opus 4.6 costs $1.56 and Claude Sonnet 4.6 $1.68.

Which has the bigger context window, Claude Opus 4.6 or Claude Sonnet 4.6?

Neither: both take 1M tokens.

How many benchmarks is the Claude Opus 4.6 vs Claude Sonnet 4.6 comparison based on?

94 benchmarks have a result for both models as of October 22, 2026. Claude Opus 4.6's coding index rests on 4 independent benchmarks and Claude Sonnet 4.6's on 5. 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-claude-sonnet-4-6" title="Claude Opus 4.6 vs Claude Sonnet 4.6, 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-claude-sonnet-4-6">LLMBenchmark.ai, Claude Opus 4.6 vs Claude Sonnet 4.6</a></p>