Enter opens the highlighted result. Esc closes.

Claude Opus 5 vs Claude Sonnet 5.5

Claude Sonnet 5.5 leads Claude Opus 5 on coding, 87.3 to 83.0 on the Vibe Coding Index, and Claude Sonnet 5.5 costs 2.5x less per output token ($10.00 vs $25.00 per million). Updated October 22, 2026; 91 benchmarks have a result for both.

Replace Claude Opus 5 Replace Claude Sonnet 5.5
Claude Opus 5Anthropic
Coding
83.0
Overall
81.6
Output $/M
$25.00
46
Claude Sonnet 5.5Anthropic
Coding
87.3
Overall
82.8
Output $/M
$10.00
43
vs boards won of 91 shared, 2 tied

Claude Opus 5 or Claude Sonnet 5.5: which to pick

Pick Claude Sonnet 5.5 for coding: it scores 87.3 on the Vibe Coding Index against 83.0 for Claude Opus 5, though on 5 benchmarks against 6.

Pick Claude Opus 5 for work measured by IOI (Vals AI) or Terminal-Bench 2.1 (Vals AI), where it leads.

Model AClaude Opus 5Anthropic83.0/1006 independent benchmarks$1.33 per solved taskModel BClaude Sonnet 5.5Anthropic87.3/1005 independent benchmarksNo cost per solved task
Shared results
91
Claude Opus 5 only
40
Claude Sonnet 5.5 only
5
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 83.0 from 6 benchmarks, Claude Sonnet 5.5 87.3 from 5 benchmarks.
Widest category
Knowledge, 9.2 points apart on average over 6 shared benchmarks.
Widest single gap
Terminal-Bench-Science (Vals AI): Claude Opus 5 27.1% against Claude Sonnet 5.5 47.1%, 20.0 points apart on a 0 to 100 scale.
Output price
Claude Opus 5 $25.00 against Claude Sonnet 5.5 $10.00 per million output tokens, 2.5x 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 5BarsClaude Sonnet 5.5Ties
Coding7111 tie
Intelligence02
Agentic work681 tie
Reasoning56
Math24
Knowledge60
Web design07
General205
All shared boards46432 ties
CodingLike-for-likeSix of these boards feed the Vibe Coding Index711
Coding benchmarks for Claude Opus 5 and Claude Sonnet 5.5
BenchmarkClaude Opus 5Claude Sonnet 5.5Leader
LiveBench coding90.8%94.7%Claude Sonnet 5.5
LMArena WebDev16891768Claude Sonnet 5.5
AA Coding Index78.0Not measuredOnly Claude Opus 5 measured
LiveCodeBench (Vals AI)89.0%Not measuredOnly Claude Opus 5 measured
SWE-bench Verified (Vals AI)97.0%Not measuredOnly Claude Opus 5 measured
Terminal-Bench 4 (Vals AI)53.5%64.1%Claude Sonnet 5.5
Vibe Code Bench (Vals AI)88.4%92.4%Claude Sonnet 5.5
Code migration (Vals AI)57.5%69.8%Claude Sonnet 5.5
ProgramBench (Vals AI)3.0%6.5%Claude Sonnet 5.5
IOI (Vals AI)84.3%83.1%Claude Opus 5
Terminal-Bench 2.1 (Vals AI)84.6%83.2%Claude Opus 5
SWE-bench Multimodal (Vals AI)Not measured58.3%Only Claude Sonnet 5.5 measured
Vibe Code Bench 1-100 (Vals AI)28.5%Not measuredOnly Claude Opus 5 measured
SkillsBench (Vals AI)60.4%Not measuredOnly Claude Opus 5 measured
CyberBench (Vals AI)65.4%59.6%Claude Opus 5
SciCode56.4%61.0%Claude Sonnet 5.5
FrontierCode53.4%52.1%Claude Opus 5
FrontierSWE52.0%61.9%Claude Sonnet 5.5
WeirdML91.8%Not measuredOnly Claude Opus 5 measured
ALE-Bench2164.61819.1Claude Opus 5
LMArena Text: coding15331513Claude Opus 5
LMArena Text: software and IT15271504Claude Opus 5
LMArena WebDev: React17111817Claude Sonnet 5.5
LMArena WebDev: HTML16801741Claude Sonnet 5.5
LMArena WebDev: from an image16621737Claude Sonnet 5.5
SciCode13.8%13.8%Tie
Neither model has a result on the other 13 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Opus 5 and Claude Sonnet 5.5
BenchmarkClaude Opus 5Claude Sonnet 5.5Leader
AA Intelligence Index50.856.0Claude Sonnet 5.5
Epoch Capabilities Index163.9166.2Claude Sonnet 5.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index68
Agentic work benchmarks for Claude Opus 5 and Claude Sonnet 5.5
BenchmarkClaude Opus 5Claude Sonnet 5.5Leader
AA Agentic Index56.5Not measuredOnly Claude Opus 5 measured
Design Arena: agents building web apps12661305Claude Sonnet 5.5
Design Arena: agents building full-stack apps1306Not measuredOnly Claude Opus 5 measured
Design Arena: agents building mobile apps13481260Claude Opus 5
Design Arena: agents building Android apps1257Not measuredOnly Claude Opus 5 measured
Design Arena: agents building Godot games1279Not measuredOnly Claude Opus 5 measured
Design Arena: agents building games1261Not measuredOnly Claude Opus 5 measured
Design Arena: PowerPoint slides1240Not measuredOnly Claude Opus 5 measured
Design Arena: spreadsheetsNot measured1260Only Claude Sonnet 5.5 measured
LiveBench research88.9%83.6%Claude Opus 5
LiveBench browser84.0%84.0%Tie
LiveBench long agentic62.1%78.8%Claude Sonnet 5.5
SREBench (Vals AI)12.2%30.1%Claude Sonnet 5.5
Finance Agent (Vals AI)58.6%58.1%Claude Opus 5
Tax Agent Bench (Vals AI)45.5%42.0%Claude Opus 5
Legal Research Bench (Vals AI)55.3%48.1%Claude Opus 5
Harvey's Legal Agent Benchmark (Vals AI)Not measured10.4%Only Claude Sonnet 5.5 measured
Excel Modeling Benchmark (Vals AI)73.6%75.7%Claude Sonnet 5.5
BioMysteryBench (Vals AI)79.3%81.1%Claude Sonnet 5.5
Terminal-Bench-Science (Vals AI)27.1%47.1%Claude Sonnet 5.5
Vals Science Index47.9%59.1%Claude Sonnet 5.5
Time Horizon Index (Vals AI)18.8%Not measuredOnly Claude Opus 5 measured
CUA-bench (Vals AI)9.0%Not measuredOnly Claude Opus 5 measured
APEX-Agents65.8%75.5%Claude Sonnet 5.5
OSWorld 2.031.4%Not measuredOnly Claude Opus 5 measured
BALROG63.4%Not measuredOnly Claude Opus 5 measured
PostTrainBench35.0%Not measuredOnly Claude Opus 5 measured
SpireClimbNot measured1.3%Only Claude Sonnet 5.5 measured
Vending-Bench 2$11,182$11,165Claude Opus 5
LMArena Search1242Not measuredOnly Claude Opus 5 measured
Neither model has a result on the other 11 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index56
Reasoning benchmarks for Claude Opus 5 and Claude Sonnet 5.5
BenchmarkClaude Opus 5Claude Sonnet 5.5Leader
GPQA Diamond93.4%Not measuredOnly Claude Opus 5 measured
LiveBench reasoning91.2%91.6%Claude Sonnet 5.5
MysteryMechanism (Vals AI)37.4%49.1%Claude Sonnet 5.5
MMMU Pro (Vals AI)89.9%Not measuredOnly Claude Opus 5 measured
GPQA Diamond (Artificial Analysis run)93.7%Not measuredOnly Claude Opus 5 measured
Humanity's Last Exam (Artificial Analysis run)54.9%55.0%Claude Sonnet 5.5
GPQA Diamond (Epoch AI run)93.9%95.6%Claude Sonnet 5.5
ARC-AGI97.5%Not measuredOnly Claude Opus 5 measured
ARC-AGI-290.4%Not measuredOnly Claude Opus 5 measured
SimpleBench80.6%Not measuredOnly Claude Opus 5 measured
Chess puzzles43.0%59.0%Claude Sonnet 5.5
Mystery game puzzles59.0%65.0%Claude Sonnet 5.5
EBR-bench45.7%Not measuredOnly Claude Opus 5 measured
LMArena Text: hard prompts15271494Claude Opus 5
LMArena Text: expert15541531Claude Opus 5
LMArena Text: hard prompts in English15231502Claude Opus 5
LMArena Vision: diagrams13481329Claude Opus 5
LMArena Vision: homework13381331Claude Opus 5
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index24
Math benchmarks for Claude Opus 5 and Claude Sonnet 5.5
BenchmarkClaude Opus 5Claude Sonnet 5.5Leader
OTIS Mock AIME98.9%100.0%Claude Sonnet 5.5
FrontierMath, tiers 1 to 385.6%88.8%Claude Sonnet 5.5
FrontierMath, tier 473.2%80.5%Claude Sonnet 5.5
ProofBench99.0%100.0%Claude Sonnet 5.5
LMArena Text: math15331497Claude Opus 5
LMArena Text: mathematical work15441510Claude Opus 5
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index60
Knowledge benchmarks for Claude Opus 5 and Claude Sonnet 5.5
BenchmarkClaude Opus 5Claude Sonnet 5.5Leader
MMLU Pro91.6%Not measuredOnly Claude Opus 5 measured
LegalBench (Vals AI)87.0%Not measuredOnly Claude Opus 5 measured
CorpFin (Vals AI)73.2%Not measuredOnly Claude Opus 5 measured
TaxEval (Vals AI)75.1%Not measuredOnly Claude Opus 5 measured
MortgageTax (Vals AI)72.1%Not measuredOnly Claude Opus 5 measured
MedCode (Vals AI)63.6%52.9%Claude Opus 5
SimpleQA Verified59.9%46.5%Claude Opus 5
LMArena Text: science15311483Claude Opus 5
LMArena Text: medicine and healthcare15251464Claude Opus 5
LMArena Text: legal and government15301483Claude Opus 5
LMArena Text: business and finance15011468Claude Opus 5
Neither model has a result on the other 7 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index07
Web design benchmarks for Claude Opus 5 and Claude Sonnet 5.5
BenchmarkClaude Opus 5Claude Sonnet 5.5Leader
Design Arena: websites13091326Claude Sonnet 5.5
Design Arena: UI components13461368Claude Sonnet 5.5
Design Arena: game dev13371471Claude Sonnet 5.5
Design Arena: data viz13291392Claude Sonnet 5.5
Design Arena: 3D13341445Claude Sonnet 5.5
Design Arena: all code categories13231364Claude Sonnet 5.5
Design Arena: SVG1311Not measuredOnly Claude Opus 5 measured
Design Arena: ASCII art1352Not measuredOnly Claude Opus 5 measured
LiveBench design83.0%85.0%Claude Sonnet 5.5
GeneralLike-for-likePublic boards, shown as published, kept out of the index205
General benchmarks for Claude Opus 5 and Claude Sonnet 5.5
BenchmarkClaude Opus 5Claude Sonnet 5.5Leader
Vals IndexNot measured70.8%Only Claude Sonnet 5.5 measured
LiveBench data analysis74.6%59.5%Claude Opus 5
Public Benefits Bench (Vals AI)76.9%67.2%Claude Opus 5
SAGE (Vals AI)49.4%51.8%Claude Sonnet 5.5
MedScribe (Vals AI)91.0%91.1%Claude Sonnet 5.5
Vals Multimodal Index73.9%Not measuredOnly Claude Opus 5 measured
Long context reasoning (AA-LCR)82.0%82.7%Claude Sonnet 5.5
DTBench97.9%97.3%Claude Opus 5
LMCA64.5%68.3%Claude Sonnet 5.5
Furniture assembly60.8%75.0%Claude Sonnet 5.5
LMArena Text15091473Claude Opus 5
LMArena Text: instruction following15181492Claude Opus 5
LMArena Text: creative writing14931467Claude Opus 5
LMArena Vision13201287Claude Opus 5
LMArena Text: English15081484Claude Opus 5
LMArena Text: non-English15021456Claude Opus 5
LMArena Text: Chinese15731535Claude Opus 5
LMArena Text: German1527Not measuredOnly Claude Opus 5 measured
LMArena Text: Japanese1520Not measuredOnly Claude Opus 5 measured
LMArena Text: Korean1517Not measuredOnly Claude Opus 5 measured
LMArena Text: French15191499Claude Opus 5
LMArena Text: Spanish15231451Claude Opus 5
LMArena Text: Russian15071454Claude Opus 5
LMArena Text: Polish1522Not measuredOnly Claude Opus 5 measured
LMArena Text: multi-turn15001465Claude Opus 5
LMArena Text: longer queries15171495Claude Opus 5
LMArena Text: writing and language14991474Claude Opus 5
LMArena Text: entertainment and media14811461Claude Opus 5
LMArena Vision: English13151289Claude Opus 5
LMArena Vision: Chinese1400Not measuredOnly Claude Opus 5 measured
LMArena Vision: reading text13291297Claude Opus 5
LMArena Vision: humor1293Not measuredOnly Claude Opus 5 measured
LMArena Vision: creative writing13131242Claude Opus 5
LMArena Document1516Not measuredOnly Claude Opus 5 measured
Neither model has a result on the other 12 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Opus 5 and Claude Sonnet 5.5
BenchmarkClaude Opus 5Claude Sonnet 5.5Leader
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$0.018Fits in one request
Claude Sonnet 5.5$0.0070Fits in one request

Claude Sonnet 5.5 costs less

Repository review

50K input + 3K output tokens

Claude Opus 5$0.325Fits in one request
Claude Sonnet 5.5$0.130Fits in one request

Claude Sonnet 5.5 costs less

Agent loop

200K input + 10K output tokens

Claude Opus 5$1.25Fits in one request
Claude Sonnet 5.5$0.500Fits in one request

Claude Sonnet 5.5 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 and Claude Sonnet 5.5
SpecificationAnthropic Claude Opus 5Anthropic Claude Sonnet 5.5
MakerAnthropicAnthropic
WeightsNo public weights listedNo public weights listed
ReleasedJuly 24, 2026September 28, 2026
Context window1M1M
Input $/Mtok$5.00$2.00
Output $/Mtok$25.00$10.00
Coding index83.087.3
Independent measurements behind it65
Cost per solved task$1.33Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 5 better than Claude Sonnet 5.5 for coding?

Pick Claude Sonnet 5.5 for coding: it scores 87.3 on the Vibe Coding Index against 83.0 for Claude Opus 5, though on 5 benchmarks against 6. Pick Claude Opus 5 for work measured by IOI (Vals AI) or Terminal-Bench 2.1 (Vals AI), where it leads.

Which is cheaper, Claude Opus 5 or Claude Sonnet 5.5?

Claude Opus 5 costs $5.00 per million input tokens and $25.00 per million output tokens; Claude Sonnet 5.5 costs $2.00 and $10.00. Cost per solved task is known for Claude Opus 5 only.

Which has the bigger context window, Claude Opus 5 or Claude Sonnet 5.5?

Neither: both take 1M tokens.

How many benchmarks is the Claude Opus 5 vs Claude Sonnet 5.5 comparison based on?

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