Enter opens the highlighted result. Esc closes.

Claude Opus 5.5 vs Claude Sonnet 4.6

Claude Opus 5.5 leads Claude Sonnet 4.6 on coding, 88.8 to 57.3 on the Vibe Coding Index, and Claude Sonnet 4.6 costs 1.3x less per output token ($15.00 vs $20.00 per million). Updated October 22, 2026; 80 benchmarks have a result for both.

Replace Claude Opus 5.5 Replace Claude Sonnet 4.6
Claude Opus 5.5Anthropic
Coding
88.8
Overall
87.1
Output $/M
$20.00
79
Claude Sonnet 4.6Anthropic
Coding
57.3
Overall
60.3
Output $/M
$15.00
1
vs boards won of 80 shared

Claude Opus 5.5 or Claude Sonnet 4.6: which to pick

Pick Claude Opus 5.5 for coding: it scores 88.8 on the Vibe Coding Index against 57.3 for Claude Sonnet 4.6.

Pick Claude Sonnet 4.6 for output tokens 1.3x cheaper ($15.00 vs $20.00 per million) and work measured by SAGE (Vals AI), where it leads.

Model AClaude Opus 5.5Anthropic88.8/1005 independent benchmarksNo cost per solved taskModel BClaude Sonnet 4.6Anthropic57.3/1005 independent benchmarks$1.68 per solved task
Shared results
80
Claude Opus 5.5 only
29
Claude Sonnet 4.6 only
38
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 5.5 88.8 from 5 benchmarks, Claude Sonnet 4.6 57.3 from 5 benchmarks.
Widest category
Intelligence, 23.8 points apart on average over 2 shared benchmarks.
Widest single gap
LiveBench long agentic: Claude Opus 5.5 85.0% against Claude Sonnet 4.6 23.1%, 61.9 points apart on a 0 to 100 scale.
Output price
Claude Opus 5.5 $20.00 against Claude Sonnet 4.6 $15.00 per million output tokens, 1.3x 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 5.5BarsClaude Sonnet 4.6Ties
Coding130
Intelligence20
Agentic work110
Reasoning120
Math40
Knowledge60
Web design80
General231
All shared boards791
CodingLike-for-likeSix of these boards feed the Vibe Coding Index130
Coding benchmarks for Claude Opus 5.5 and Claude Sonnet 4.6
BenchmarkClaude Opus 5.5Claude Sonnet 4.6Leader
LiveBench coding96.3%66.6%Claude Opus 5.5
LMArena WebDev18071523Claude Opus 5.5
AA Coding IndexNot measured63.0Only Claude Sonnet 4.6 measured
LiveCodeBench (Vals AI)Not measured82.1%Only Claude Sonnet 4.6 measured
SWE-bench Verified (Vals AI)Not measured77.4%Only Claude Sonnet 4.6 measured
Terminal-Bench 4 (Vals AI)65.2%Not measuredOnly Claude Opus 5.5 measured
Vibe Code Bench (Vals AI)90.3%55.8%Claude Opus 5.5
Code migration (Vals AI)66.7%39.9%Claude Opus 5.5
ProgramBench (Vals AI)18.5%0.5%Claude Opus 5.5
IOI (Vals AI)95.1%Not measuredOnly Claude Opus 5.5 measured
Terminal-Bench 2.1 (Vals AI)87.6%57.3%Claude Opus 5.5
SWE-bench Multimodal (Vals AI)70.2%Not measuredOnly Claude Opus 5.5 measured
Vibe Code Bench 1-100 (Vals AI)30.4%Not measuredOnly Claude Opus 5.5 measured
SkillsBench (Vals AI)Not measured49.0%Only Claude Sonnet 4.6 measured
CyberBench (Vals AI)74.6%Not measuredOnly Claude Opus 5.5 measured
SciCode66.9%50.1%Claude Opus 5.5
Terminal-Bench Hard (Artificial Analysis run)Not measured53.0%Only Claude Sonnet 4.6 measured
Terminal-BenchNot measured53.4%Only Claude Sonnet 4.6 measured
FrontierCode54.6%24.3%Claude Opus 5.5
FrontierSWE62.3%Not measuredOnly Claude Opus 5.5 measured
WeirdMLNot measured66.1%Only Claude Sonnet 4.6 measured
MirrorCode77.4%Not measuredOnly Claude Opus 5.5 measured
ALE-Bench2147.4Not measuredOnly Claude Opus 5.5 measured
LMArena Text: coding15451503Claude Opus 5.5
LMArena Text: software and IT15381491Claude Opus 5.5
LMArena WebDev: React18551512Claude Opus 5.5
LMArena WebDev: HTML17531527Claude Opus 5.5
LMArena WebDev: from an image17531529Claude Opus 5.5
SciCode18.5%Not measuredOnly Claude Opus 5.5 measured
Neither model has a result on the other 10 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Opus 5.5 and Claude Sonnet 4.6
BenchmarkClaude Opus 5.5Claude Sonnet 4.6Leader
AA Intelligence Index57.630.1Claude Opus 5.5
Epoch Capabilities Index168.8152.8Claude Opus 5.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index110
Agentic work benchmarks for Claude Opus 5.5 and Claude Sonnet 4.6
BenchmarkClaude Opus 5.5Claude Sonnet 4.6Leader
AA Agentic IndexNot measured31.8Only Claude Sonnet 4.6 measured
Design Arena: agents building web apps13161190Claude Opus 5.5
Design Arena: agents building full-stack appsNot measured1213Only Claude Sonnet 4.6 measured
Design Arena: agents building mobile apps13091211Claude Opus 5.5
Design Arena: agents building Android appsNot measured1197Only Claude Sonnet 4.6 measured
Design Arena: agents building Godot gamesNot measured1226Only Claude Sonnet 4.6 measured
Design Arena: agents building gamesNot measured1177Only Claude Sonnet 4.6 measured
Design Arena: spreadsheets1386Not measuredOnly Claude Opus 5.5 measured
LiveBench research85.0%63.6%Claude Opus 5.5
LiveBench browser80.0%68.0%Claude Opus 5.5
LiveBench long agentic85.0%23.1%Claude Opus 5.5
SREBench (Vals AI)33.6%Not measuredOnly Claude Opus 5.5 measured
Finance Agent (Vals AI)58.6%51.0%Claude Opus 5.5
Tax Agent Bench (Vals AI)45.6%25.8%Claude Opus 5.5
Legal Research Bench (Vals AI)50.5%38.5%Claude Opus 5.5
Harvey's Legal Agent Benchmark (Vals AI)9.2%Not measuredOnly Claude Opus 5.5 measured
Excel Modeling Benchmark (Vals AI)75.9%60.2%Claude Opus 5.5
BioMysteryBench (Vals AI)79.3%Not measuredOnly Claude Opus 5.5 measured
Terminal-Bench-Science (Vals AI)47.1%Not measuredOnly Claude Opus 5.5 measured
Vals Science Index58.7%Not measuredOnly Claude Opus 5.5 measured
Time Horizon Index (Vals AI)91.3%Not measuredOnly Claude Opus 5.5 measured
CUA-bench (Vals AI)14.0%Not measuredOnly Claude Opus 5.5 measured
Robo-bench (Vals AI)14.6%Not measuredOnly Claude Opus 5.5 measured
τ²-Bench TelecomNot measured79.5%Only Claude Sonnet 4.6 measured
APEX-Agents73.5%43.0%Claude Opus 5.5
Remote Labor Index21.3%Not measuredOnly Claude Opus 5.5 measured
OSWorld 2.0Not measured9.3%Only Claude Sonnet 4.6 measured
DeepResearch BenchNot measured54.9%Only Claude Sonnet 4.6 measured
OSWorldNot measured72.1%Only Claude Sonnet 4.6 measured
SpireClimb3.3%Not measuredOnly Claude Opus 5.5 measured
Vending-Bench 2$9,235$7,204Claude Opus 5.5
LMArena Search1213Not measuredOnly Claude Opus 5.5 measured
Neither model has a result on the other 9 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index120
Reasoning benchmarks for Claude Opus 5.5 and Claude Sonnet 4.6
BenchmarkClaude Opus 5.5Claude Sonnet 4.6Leader
GPQA DiamondNot measured85.6%Only Claude Sonnet 4.6 measured
LiveBench reasoning92.2%86.4%Claude Opus 5.5
MysteryMechanism (Vals AI)49.5%Not measuredOnly Claude Opus 5.5 measured
MMMU Pro (Vals AI)Not measured83.6%Only Claude Sonnet 4.6 measured
GPQA Diamond (Artificial Analysis run)Not measured87.5%Only Claude Sonnet 4.6 measured
Humanity's Last Exam (Artificial Analysis run)61.4%33.6%Claude Opus 5.5
GPQA Diamond (Epoch AI run)90.6%87.4%Claude Opus 5.5
ARC-AGI98.5%86.5%Claude Opus 5.5
ARC-AGI-293.3%60.4%Claude Opus 5.5
Chess puzzles67.0%23.0%Claude Opus 5.5
Mystery game puzzles71.0%16.0%Claude Opus 5.5
EBR-bench71.4%Not measuredOnly Claude Opus 5.5 measured
LMArena Text: hard prompts15361485Claude Opus 5.5
LMArena Text: expert15491500Claude Opus 5.5
LMArena Text: hard prompts in English15351493Claude Opus 5.5
LMArena Vision: diagrams13451306Claude Opus 5.5
LMArena Vision: homework13621311Claude Opus 5.5
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index40
Math benchmarks for Claude Opus 5.5 and Claude Sonnet 4.6
BenchmarkClaude Opus 5.5Claude Sonnet 4.6Leader
AIMENot measured92.3%Only Claude Sonnet 4.6 measured
OTIS Mock AIME100.0%85.8%Claude Opus 5.5
FrontierMath, tiers 1 to 391.2%Not measuredOnly Claude Opus 5.5 measured
FrontierMath, tier 495.0%Not measuredOnly Claude Opus 5.5 measured
ProofBench100.0%45.0%Claude Opus 5.5
LMArena Text: math15181462Claude Opus 5.5
LMArena Text: mathematical work15161483Claude Opus 5.5
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index60
Knowledge benchmarks for Claude Opus 5.5 and Claude Sonnet 4.6
BenchmarkClaude Opus 5.5Claude Sonnet 4.6Leader
MMLU ProNot measured87.3%Only Claude Sonnet 4.6 measured
LegalBench (Vals AI)Not measured82.1%Only Claude Sonnet 4.6 measured
CaseLaw (Vals AI)Not measured64.0%Only Claude Sonnet 4.6 measured
CorpFin (Vals AI)Not measured65.3%Only Claude Sonnet 4.6 measured
TaxEval (Vals AI)Not measured77.1%Only Claude Sonnet 4.6 measured
MortgageTax (Vals AI)Not measured67.7%Only Claude Sonnet 4.6 measured
MedQA (Vals AI)Not measured92.1%Only Claude Sonnet 4.6 measured
MedCode (Vals AI)49.8%Not measuredOnly Claude Opus 5.5 measured
SimpleQA Verified72.2%35.5%Claude Opus 5.5
LMArena Text: science15241474Claude Opus 5.5
LMArena Text: medicine and healthcare15091451Claude Opus 5.5
LMArena Text: legal and government15181470Claude Opus 5.5
LMArena Text: business and finance14941464Claude Opus 5.5
FACTS Benchmark Suite65.3%37.0%Claude Opus 5.5
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 5.5 and Claude Sonnet 4.6
BenchmarkClaude Opus 5.5Claude Sonnet 4.6Leader
Design Arena: websites13351284Claude Opus 5.5
Design Arena: UI components13821269Claude Opus 5.5
Design Arena: game dev14551258Claude Opus 5.5
Design Arena: data viz13981278Claude Opus 5.5
Design Arena: 3D14761234Claude Opus 5.5
Design Arena: all code categories13881275Claude Opus 5.5
Design Arena: SVG13281196Claude Opus 5.5
Design Arena: ASCII artNot measured1235Only Claude Sonnet 4.6 measured
LiveBench design86.9%71.8%Claude Opus 5.5
GeneralLike-for-likePublic boards, shown as published, kept out of the index231
General benchmarks for Claude Opus 5.5 and Claude Sonnet 4.6
BenchmarkClaude Opus 5.5Claude Sonnet 4.6Leader
Vals Index70.2%Not measuredOnly Claude Opus 5.5 measured
LiveBench data analysis80.3%76.1%Claude Opus 5.5
Public Benefits Bench (Vals AI)70.6%62.5%Claude Opus 5.5
SAGE (Vals AI)45.8%46.6%Claude Sonnet 4.6
MedScribe (Vals AI)91.4%Not measuredOnly Claude Opus 5.5 measured
Vals Multimodal IndexNot measured60.6%Only Claude Sonnet 4.6 measured
IFBenchNot measured56.6%Only Claude Sonnet 4.6 measured
Long context reasoning (AA-LCR)84.7%80.0%Claude Opus 5.5
DTBench98.9%89.9%Claude Opus 5.5
LMCA68.2%46.5%Claude Opus 5.5
Furniture assembly83.3%Not measuredOnly Claude Opus 5.5 measured
ExploitBenchNot measured23.6%Only Claude Sonnet 4.6 measured
LMArena Text15161458Claude Opus 5.5
LMArena Text: instruction following15371476Claude Opus 5.5
LMArena Text: creative writing15351435Claude Opus 5.5
LMArena Vision13211283Claude Opus 5.5
LMArena Text: English15191472Claude Opus 5.5
LMArena Text: non-English15071440Claude Opus 5.5
LMArena Text: Chinese15821491Claude Opus 5.5
LMArena Text: GermanNot measured1428Only Claude Sonnet 4.6 measured
LMArena Text: Japanese15341420Claude Opus 5.5
LMArena Text: KoreanNot measured1410Only Claude Sonnet 4.6 measured
LMArena Text: French14931465Claude Opus 5.5
LMArena Text: Spanish15081464Claude Opus 5.5
LMArena Text: Russian15171440Claude Opus 5.5
LMArena Text: PolishNot measured1443Only Claude Sonnet 4.6 measured
LMArena Text: multi-turn15011464Claude Opus 5.5
LMArena Text: longer queries15321479Claude Opus 5.5
LMArena Text: writing and language15321444Claude Opus 5.5
LMArena Text: entertainment and media15151431Claude Opus 5.5
LMArena Vision: English13171298Claude Opus 5.5
LMArena Vision: ChineseNot measured1307Only Claude Sonnet 4.6 measured
LMArena Vision: reading text13261296Claude Opus 5.5
LMArena Vision: humorNot measured1248Only Claude Sonnet 4.6 measured
LMArena Vision: recognizing thingsNot measured1195Only Claude Sonnet 4.6 measured
LMArena Vision: creative writing13201272Claude Opus 5.5
LMArena DocumentNot measured1482Only Claude Sonnet 4.6 measured
Neither model has a result on the other 9 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Opus 5.5 and Claude Sonnet 4.6
BenchmarkClaude Opus 5.5Claude 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 5.5$0.014Fits 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 5.5$0.260Fits 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 5.5$1.00Fits 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 5.5 and Claude Sonnet 4.6
SpecificationAnthropic Claude Opus 5.5Anthropic Claude Sonnet 4.6
MakerAnthropicAnthropic
WeightsNo public weights listedNo public weights listed
ReleasedSeptember 22, 2026February 17, 2026
Context window1M1M
Input $/Mtok$4.00$3.00
Output $/Mtok$20.00$15.00
Coding index88.857.3
Independent measurements behind it55
Cost per solved taskNot computable$1.68
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 5.5 better than Claude Sonnet 4.6 for coding?

Pick Claude Opus 5.5 for coding: it scores 88.8 on the Vibe Coding Index against 57.3 for Claude Sonnet 4.6. Pick Claude Sonnet 4.6 for output tokens 1.3x cheaper ($15.00 vs $20.00 per million) and work measured by SAGE (Vals AI), where it leads.

Which is cheaper, Claude Opus 5.5 or Claude Sonnet 4.6?

Claude Opus 5.5 costs $4.00 per million input tokens and $20.00 per million output tokens; Claude Sonnet 4.6 costs $3.00 and $15.00. Cost per solved task is known for Claude Sonnet 4.6 only.

Which has the bigger context window, Claude Opus 5.5 or Claude Sonnet 4.6?

Neither: both take 1M tokens.

How many benchmarks is the Claude Opus 5.5 vs Claude Sonnet 4.6 comparison based on?

80 benchmarks have a result for both models as of October 22, 2026. Claude Opus 5.5's coding index rests on 5 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-5-5-vs-claude-sonnet-4-6" title="Claude Opus 5.5 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-5-5-vs-claude-sonnet-4-6">LLMBenchmark.ai, Claude Opus 5.5 vs Claude Sonnet 4.6</a></p>