Enter opens the highlighted result. Esc closes.

Claude Opus 5 vs Claude Sonnet 5

Claude Opus 5 leads Claude Sonnet 5 on coding, 83.0 to 57.7 on the Vibe Coding Index, and Claude Sonnet 5 costs 2.5x less per output token ($10.00 vs $25.00 per million). Updated October 22, 2026; 117 benchmarks have a result for both.

Replace Claude Opus 5 Replace Claude Sonnet 5
Claude Opus 5Anthropic
Coding
83.0
Overall
81.6
Output $/M
$25.00
113
Claude Sonnet 5Anthropic
Coding
57.7
Overall
63.2
Output $/M
$10.00
3
vs boards won of 117 shared, 1 tied

Claude Opus 5 or Claude Sonnet 5: which to pick

Pick Claude Opus 5 for coding: it scores 83.0 on the Vibe Coding Index against 57.7 for Claude Sonnet 5.

Pick Claude Sonnet 5 for output tokens 2.5x cheaper ($10.00 vs $25.00 per million) and work measured by CyberBench (Vals AI) or Chess puzzles, where it leads.

Model AClaude Opus 5Anthropic83.0/1006 independent benchmarks$1.33 per solved taskModel BClaude Sonnet 5Anthropic57.7/1006 independent benchmarks$1.87 per solved task
Shared results
117
Claude Opus 5 only
14
Claude Sonnet 5 only
4
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 57.7 from 6 benchmarks.
Widest category
Math, 18.6 points apart on average over 6 shared benchmarks.
Widest single gap
Terminal-Bench 4 (Vals AI): Claude Opus 5 53.5% against Claude Sonnet 5 10.6%, 57.2 points apart on a 0 to 100 scale.
Output price
Claude Opus 5 $25.00 against Claude Sonnet 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 5Ties
Coding231
Intelligence20
Agentic work190
Reasoning131
Math60
Knowledge101
Web design90
General3101 tie
All shared boards11331 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index231
Coding benchmarks for Claude Opus 5 and Claude Sonnet 5
BenchmarkClaude Opus 5Claude Sonnet 5Leader
LiveBench coding90.8%74.7%Claude Opus 5
LMArena WebDev16891540Claude Opus 5
AA Coding Index78.071.5Claude Opus 5
LiveCodeBench (Vals AI)89.0%82.4%Claude Opus 5
SWE-bench Verified (Vals AI)97.0%79.6%Claude Opus 5
Terminal-Bench 4 (Vals AI)53.5%10.6%Claude Opus 5
Vibe Code Bench (Vals AI)88.4%81.3%Claude Opus 5
Code migration (Vals AI)57.5%44.4%Claude Opus 5
ProgramBench (Vals AI)3.0%0.0%Claude Opus 5
IOI (Vals AI)84.3%45.0%Claude Opus 5
Terminal-Bench 2.1 (Vals AI)84.6%74.5%Claude Opus 5
Vibe Code Bench 1-100 (Vals AI)28.5%13.8%Claude Opus 5
SkillsBench (Vals AI)60.4%46.5%Claude Opus 5
CyberBench (Vals AI)65.4%70.3%Claude Sonnet 5
SciCode56.4%54.3%Claude Opus 5
FrontierCode53.4%42.7%Claude Opus 5
FrontierSWE52.0%Not measuredOnly Claude Opus 5 measured
GSO-BenchNot measured37.3%Only Claude Sonnet 5 measured
WeirdML91.8%68.8%Claude Opus 5
ALE-Bench2164.61463.1Claude Opus 5
LMArena Text: coding15331483Claude Opus 5
LMArena Text: software and IT15271474Claude Opus 5
LMArena WebDev: React17111541Claude Opus 5
LMArena WebDev: HTML16801527Claude Opus 5
LMArena WebDev: from an image16621540Claude Opus 5
SciCode13.8%10.7%Claude Opus 5
Neither model has a result on the other 13 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Opus 5 and Claude Sonnet 5
BenchmarkClaude Opus 5Claude Sonnet 5Leader
AA Intelligence Index50.838.2Claude Opus 5
Epoch Capabilities Index163.9156.9Claude Opus 5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index190
Agentic work benchmarks for Claude Opus 5 and Claude Sonnet 5
BenchmarkClaude Opus 5Claude Sonnet 5Leader
AA Agentic Index56.543.6Claude Opus 5
Design Arena: agents building web apps12661245Claude Opus 5
Design Arena: agents building full-stack apps13061249Claude Opus 5
Design Arena: agents building mobile apps13481215Claude Opus 5
Design Arena: agents building Android apps12571227Claude Opus 5
Design Arena: agents building Godot games12791225Claude Opus 5
Design Arena: agents building games12611227Claude Opus 5
Design Arena: HTML slidesNot measured1168Only Claude Sonnet 5 measured
Design Arena: PowerPoint slides12401191Claude Opus 5
Design Arena: spreadsheetsNot measured1035Only Claude Sonnet 5 measured
LiveBench research88.9%82.8%Claude Opus 5
LiveBench browser84.0%72.0%Claude Opus 5
LiveBench long agentic62.1%39.0%Claude Opus 5
SREBench (Vals AI)12.2%0.4%Claude Opus 5
Finance Agent (Vals AI)58.6%53.9%Claude Opus 5
Tax Agent Bench (Vals AI)45.5%29.4%Claude Opus 5
Legal Research Bench (Vals AI)55.3%41.8%Claude Opus 5
Excel Modeling Benchmark (Vals AI)73.6%66.3%Claude Opus 5
BioMysteryBench (Vals AI)79.3%Not measuredOnly Claude Opus 5 measured
Terminal-Bench-Science (Vals AI)27.1%5.7%Claude Opus 5
Vals Science Index47.9%Not measuredOnly Claude Opus 5 measured
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%54.5%Claude Opus 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
Vending-Bench 2$11,182$6,378Claude Opus 5
LMArena Search1242Not measuredOnly Claude Opus 5 measured
Neither model has a result on the other 12 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index131
Reasoning benchmarks for Claude Opus 5 and Claude Sonnet 5
BenchmarkClaude Opus 5Claude Sonnet 5Leader
GPQA Diamond93.4%88.9%Claude Opus 5
LiveBench reasoning91.2%88.7%Claude Opus 5
MysteryMechanism (Vals AI)37.4%Not measuredOnly Claude Opus 5 measured
MMMU Pro (Vals AI)89.9%83.0%Claude Opus 5
GPQA Diamond (Artificial Analysis run)93.7%91.1%Claude Opus 5
Humanity's Last Exam (Artificial Analysis run)54.9%41.3%Claude Opus 5
GPQA Diamond (Epoch AI run)93.9%90.5%Claude Opus 5
ARC-AGI97.5%Not measuredOnly Claude Opus 5 measured
ARC-AGI-290.4%Not measuredOnly Claude Opus 5 measured
SimpleBench80.6%60.6%Claude Opus 5
Chess puzzles43.0%45.0%Claude Sonnet 5
Mystery game puzzles59.0%35.0%Claude Opus 5
EBR-bench45.7%Not measuredOnly Claude Opus 5 measured
LMArena Text: hard prompts15271461Claude Opus 5
LMArena Text: expert15541489Claude Opus 5
LMArena Text: hard prompts in English15231464Claude Opus 5
LMArena Vision: diagrams13481293Claude Opus 5
LMArena Vision: homework13381311Claude Opus 5
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for Claude Opus 5 and Claude Sonnet 5
BenchmarkClaude Opus 5Claude Sonnet 5Leader
OTIS Mock AIME98.9%94.7%Claude Opus 5
FrontierMath, tiers 1 to 385.6%65.6%Claude Opus 5
FrontierMath, tier 473.2%29.3%Claude Opus 5
ProofBench99.0%77.0%Claude Opus 5
LMArena Text: math15331467Claude Opus 5
LMArena Text: mathematical work15441481Claude Opus 5
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index101
Knowledge benchmarks for Claude Opus 5 and Claude Sonnet 5
BenchmarkClaude Opus 5Claude Sonnet 5Leader
MMLU Pro91.6%87.5%Claude Opus 5
LegalBench (Vals AI)87.0%83.9%Claude Opus 5
CorpFin (Vals AI)73.2%67.0%Claude Opus 5
TaxEval (Vals AI)75.1%75.6%Claude Sonnet 5
MortgageTax (Vals AI)72.1%70.0%Claude Opus 5
MedCode (Vals AI)63.6%47.5%Claude Opus 5
SimpleQA Verified59.9%33.7%Claude Opus 5
LMArena Text: science15311460Claude Opus 5
LMArena Text: medicine and healthcare15251442Claude Opus 5
LMArena Text: legal and government15301454Claude Opus 5
LMArena Text: business and finance15011436Claude 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 index90
Web design benchmarks for Claude Opus 5 and Claude Sonnet 5
BenchmarkClaude Opus 5Claude Sonnet 5Leader
Design Arena: websites13091274Claude Opus 5
Design Arena: UI components13461277Claude Opus 5
Design Arena: game dev13371277Claude Opus 5
Design Arena: data viz13291251Claude Opus 5
Design Arena: 3D13341261Claude Opus 5
Design Arena: all code categories13231275Claude Opus 5
Design Arena: SVG13111192Claude Opus 5
Design Arena: ASCII art13521207Claude Opus 5
LiveBench design83.0%82.0%Claude Opus 5
GeneralLike-for-likePublic boards, shown as published, kept out of the index310
General benchmarks for Claude Opus 5 and Claude Sonnet 5
BenchmarkClaude Opus 5Claude Sonnet 5Leader
LiveBench data analysis74.6%71.7%Claude Opus 5
Public Benefits Bench (Vals AI)76.9%66.0%Claude Opus 5
SAGE (Vals AI)49.4%48.9%Claude Opus 5
MedScribe (Vals AI)91.0%76.0%Claude Opus 5
Vals Multimodal Index73.9%68.8%Claude Opus 5
Long context reasoning (AA-LCR)82.0%82.0%Tie
DTBench97.9%92.5%Claude Opus 5
LMCA64.5%50.0%Claude Opus 5
Surface Evolver BenchNot measured60.0%Only Claude Sonnet 5 measured
Furniture assembly60.8%Not measuredOnly Claude Opus 5 measured
LMArena Text15091442Claude Opus 5
LMArena Text: instruction following15181452Claude Opus 5
LMArena Text: creative writing14931416Claude Opus 5
LMArena Vision13201273Claude Opus 5
LMArena Text: English15081450Claude Opus 5
LMArena Text: non-English15021431Claude Opus 5
LMArena Text: Chinese15731478Claude Opus 5
LMArena Text: German15271442Claude Opus 5
LMArena Text: Japanese15201422Claude Opus 5
LMArena Text: Korean15171412Claude Opus 5
LMArena Text: French15191463Claude Opus 5
LMArena Text: Spanish15231438Claude Opus 5
LMArena Text: Russian15071450Claude Opus 5
LMArena Text: Polish15221425Claude Opus 5
LMArena Text: multi-turn15001453Claude Opus 5
LMArena Text: longer queries15171462Claude Opus 5
LMArena Text: writing and language14991436Claude Opus 5
LMArena Text: entertainment and media14811411Claude Opus 5
LMArena Vision: English13151275Claude Opus 5
LMArena Vision: Chinese14001331Claude Opus 5
LMArena Vision: reading text13291288Claude Opus 5
LMArena Vision: humor12931261Claude Opus 5
LMArena Vision: creative writing13131246Claude Opus 5
LMArena Document15161466Claude Opus 5
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
BenchmarkClaude Opus 5Claude Sonnet 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$0.0070Fits in one request

Claude Sonnet 5 costs less

Repository review

50K input + 3K output tokens

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

Claude Sonnet 5 costs less

Agent loop

200K input + 10K output tokens

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

Claude Sonnet 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
SpecificationAnthropic Claude Opus 5Anthropic Claude Sonnet 5
MakerAnthropicAnthropic
WeightsNo public weights listedNo public weights listed
ReleasedJuly 24, 2026June 30, 2026
Context window1M1M
Input $/Mtok$5.00$2.00
Output $/Mtok$25.00$10.00
Coding index83.057.7
Independent measurements behind it66
Cost per solved task$1.33$1.87
SourceOpenRouter listingOpenRouter listing

Questions

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

Pick Claude Opus 5 for coding: it scores 83.0 on the Vibe Coding Index against 57.7 for Claude Sonnet 5. Pick Claude Sonnet 5 for output tokens 2.5x cheaper ($10.00 vs $25.00 per million) and work measured by CyberBench (Vals AI) or Chess puzzles, where it leads.

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

Claude Opus 5 costs $5.00 per million input tokens and $25.00 per million output tokens; Claude Sonnet 5 costs $2.00 and $10.00. Per solved SWE-bench Verified task, Claude Opus 5 costs $1.33 and Claude Sonnet 5 $1.87.

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

Neither: both take 1M tokens.

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

117 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's on 6. 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" title="Claude Opus 5 vs Claude Sonnet 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">LLMBenchmark.ai, Claude Opus 5 vs Claude Sonnet 5</a></p>