Enter opens the highlighted result. Esc closes.

Claude Opus 4.6 vs Claude Opus 5

Claude Opus 5 leads Claude Opus 4.6 on coding, 83.0 to 57.2 on the Vibe Coding Index, at about the same output price ($25.00 vs $25.00 per million). Updated October 22, 2026; 91 benchmarks have a result for both.

Replace Claude Opus 4.6 Replace Claude Opus 5
Claude Opus 4.6Anthropic
Coding
57.2
Overall
66.0
Output $/M
$25.00
15
Claude Opus 5Anthropic
Coding
83.0
Overall
81.6
Output $/M
$25.00
76
vs boards won of 91 shared

Claude Opus 4.6 or Claude Opus 5: which to pick

Pick Claude Opus 5 for coding: it scores 83.0 on the Vibe Coding Index against 57.2 for Claude Opus 4.6.

Pick Claude Opus 4.6 for work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.

Model AClaude Opus 4.6Anthropic57.2/1004 independent benchmarks$1.56 per solved taskModel BClaude Opus 5Anthropic83.0/1006 independent benchmarks$1.33 per solved task
Shared results
91
Claude Opus 4.6 only
19
Claude Opus 5 only
40
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 Opus 5 83.0 from 6 benchmarks.
Widest category
Math, 20.8 points apart on average over 6 shared benchmarks.
Widest single gap
ProofBench: Claude Opus 4.6 50.0% against Claude Opus 5 99.0%, 49.0 points apart on a 0 to 100 scale.
Output price
Both cost $25.00 per million output tokens.
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 Opus 5Ties
Coding29
Intelligence02
Agentic work07
Reasoning115
Math06
Knowledge110
Web design08
General1119
All shared boards1576
CodingLike-for-likeSix of these boards feed the Vibe Coding Index29
Coding benchmarks for Claude Opus 4.6 and Claude Opus 5
BenchmarkClaude Opus 4.6Claude Opus 5Leader
SWE-bench Verified75.6%Not measuredOnly Claude Opus 4.6 measured
SWE-bench Multilingual72.0%Not measuredOnly Claude Opus 4.6 measured
LiveBench codingNot measured90.8%Only Claude Opus 5 measured
LMArena WebDev15471689Claude Opus 5
AA Coding IndexNot measured78.0Only Claude Opus 5 measured
LiveCodeBench (Vals AI)84.7%89.0%Claude Opus 5
SWE-bench Verified (Vals AI)78.2%97.0%Claude Opus 5
Terminal-Bench 4 (Vals AI)Not measured53.5%Only Claude Opus 5 measured
Vibe Code Bench (Vals AI)57.6%88.4%Claude Opus 5
Code migration (Vals AI)Not measured57.5%Only Claude Opus 5 measured
ProgramBench (Vals AI)Not measured3.0%Only Claude Opus 5 measured
IOI (Vals AI)Not measured84.3%Only Claude Opus 5 measured
Terminal-Bench 2.1 (Vals AI)Not measured84.6%Only Claude Opus 5 measured
Vibe Code Bench 1-100 (Vals AI)Not measured28.5%Only Claude Opus 5 measured
SkillsBench (Vals AI)Not measured60.4%Only Claude Opus 5 measured
CyberBench (Vals AI)Not measured65.4%Only Claude Opus 5 measured
SciCodeNot measured56.4%Only Claude Opus 5 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%53.4%Claude Opus 5
FrontierSWENot measured52.0%Only Claude Opus 5 measured
GSO-Bench41.2%Not measuredOnly Claude Opus 4.6 measured
WeirdML78.0%91.8%Claude Opus 5
Cybench93.0%Not measuredOnly Claude Opus 4.6 measured
ALE-BenchNot measured2164.6Only Claude Opus 5 measured
LMArena Text: coding15341533Claude Opus 4.6
LMArena Text: software and IT15271527Claude Opus 4.6
LMArena WebDev: React15391711Claude Opus 5
LMArena WebDev: HTML15591680Claude Opus 5
LMArena WebDev: from an image15431662Claude Opus 5
SciCodeNot measured13.8%Only Claude Opus 5 measured
Neither model has a result on the other 8 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Opus 4.6 and Claude Opus 5
BenchmarkClaude Opus 4.6Claude Opus 5Leader
AA Intelligence Index31.950.8Claude Opus 5
Epoch Capabilities Index155.7163.9Claude Opus 5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index07
Agentic work benchmarks for Claude Opus 4.6 and Claude Opus 5
BenchmarkClaude Opus 4.6Claude Opus 5Leader
AA Agentic IndexNot measured56.5Only Claude Opus 5 measured
Design Arena: agents building web apps12061266Claude Opus 5
Design Arena: agents building full-stack apps12201306Claude Opus 5
Design Arena: agents building mobile apps12071348Claude Opus 5
Design Arena: agents building Android apps11971257Claude Opus 5
Design Arena: agents building Godot gamesNot measured1279Only Claude Opus 5 measured
Design Arena: agents building games12121261Claude Opus 5
Design Arena: PowerPoint slidesNot measured1240Only Claude Opus 5 measured
LiveBench researchNot measured88.9%Only Claude Opus 5 measured
LiveBench browserNot measured84.0%Only Claude Opus 5 measured
LiveBench long agenticNot measured62.1%Only Claude Opus 5 measured
SREBench (Vals AI)Not measured12.2%Only Claude Opus 5 measured
Finance Agent (Vals AI)Not measured58.6%Only Claude Opus 5 measured
Tax Agent Bench (Vals AI)Not measured45.5%Only Claude Opus 5 measured
Legal Research Bench (Vals AI)Not measured55.3%Only Claude Opus 5 measured
Excel Modeling Benchmark (Vals AI)Not measured73.6%Only Claude Opus 5 measured
BioMysteryBench (Vals AI)Not measured79.3%Only Claude Opus 5 measured
Terminal-Bench-Science (Vals AI)Not measured27.1%Only Claude Opus 5 measured
Vals Science IndexNot measured47.9%Only Claude Opus 5 measured
Time Horizon Index (Vals AI)Not measured18.8%Only Claude Opus 5 measured
CUA-bench (Vals AI)Not measured9.0%Only Claude Opus 5 measured
τ²-Bench Telecom92.1%Not measuredOnly Claude Opus 4.6 measured
APEX-Agents46.3%65.8%Claude Opus 5
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 measured31.4%Only Claude Opus 5 measured
BALROGNot measured63.4%Only Claude Opus 5 measured
DeepResearch Bench55.3%Not measuredOnly Claude Opus 4.6 measured
PostTrainBenchNot measured35.0%Only Claude Opus 5 measured
Vending-Bench 2$8,018$11,182Claude Opus 5
LMArena SearchNot measured1242Only Claude Opus 5 measured
Neither model has a result on the other 10 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index115
Reasoning benchmarks for Claude Opus 4.6 and Claude Opus 5
BenchmarkClaude Opus 4.6Claude Opus 5Leader
GPQA Diamond89.7%93.4%Claude Opus 5
LiveBench reasoningNot measured91.2%Only Claude Opus 5 measured
MysteryMechanism (Vals AI)Not measured37.4%Only Claude Opus 5 measured
MMMU Pro (Vals AI)83.9%89.9%Claude Opus 5
GPQA Diamond (Artificial Analysis run)89.6%93.7%Claude Opus 5
Humanity's Last Exam (Artificial Analysis run)39.9%54.9%Claude Opus 5
GPQA Diamond (Epoch AI run)90.5%93.9%Claude Opus 5
ARC-AGI94.0%97.5%Claude Opus 5
ARC-AGI-269.2%90.4%Claude Opus 5
SimpleBench67.6%80.6%Claude Opus 5
Chess puzzles21.0%43.0%Claude Opus 5
Mystery game puzzles25.0%59.0%Claude Opus 5
EBR-bench12.7%45.7%Claude Opus 5
LMArena Text: hard prompts15251527Claude Opus 5
LMArena Text: expert15441554Claude Opus 5
LMArena Text: hard prompts in English15301523Claude Opus 4.6
LMArena Vision: diagrams13401348Claude Opus 5
LMArena Vision: homework13371338Claude Opus 5
Kagi LLM Benchmark83.6%Not measuredOnly Claude Opus 4.6 measured
Neither model has a result on the other 3 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index06
Math benchmarks for Claude Opus 4.6 and Claude Opus 5
BenchmarkClaude Opus 4.6Claude Opus 5Leader
AIME95.6%Not measuredOnly Claude Opus 4.6 measured
OTIS Mock AIME94.4%98.9%Claude Opus 5
FrontierMath, tiers 1 to 366.0%85.6%Claude Opus 5
FrontierMath, tier 426.8%73.2%Claude Opus 5
ProofBench50.0%99.0%Claude Opus 5
LMArena Text: math15181533Claude Opus 5
LMArena Text: mathematical work15251544Claude Opus 5
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index110
Knowledge benchmarks for Claude Opus 4.6 and Claude Opus 5
BenchmarkClaude Opus 4.6Claude Opus 5Leader
MMLU Pro89.1%91.6%Claude Opus 5
LegalBench (Vals AI)85.3%87.0%Claude Opus 5
CaseLaw (Vals AI)62.1%Not measuredOnly Claude Opus 4.6 measured
CorpFin (Vals AI)67.0%73.2%Claude Opus 5
TaxEval (Vals AI)76.0%75.1%Claude Opus 4.6
MortgageTax (Vals AI)68.5%72.1%Claude Opus 5
MedQA (Vals AI)95.4%Not measuredOnly Claude Opus 4.6 measured
MedCode (Vals AI)49.1%63.6%Claude Opus 5
SimpleQA Verified47.0%59.9%Claude Opus 5
LMArena Text: science15191531Claude Opus 5
LMArena Text: medicine and healthcare15041525Claude Opus 5
LMArena Text: legal and government15121530Claude Opus 5
LMArena Text: business and finance14971501Claude Opus 5
FACTS Benchmark Suite41.5%Not measuredOnly Claude Opus 4.6 measured
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index08
Web design benchmarks for Claude Opus 4.6 and Claude Opus 5
BenchmarkClaude Opus 4.6Claude Opus 5Leader
Design Arena: websites12911309Claude Opus 5
Design Arena: UI components12811346Claude Opus 5
Design Arena: game dev12771337Claude Opus 5
Design Arena: data viz12791329Claude Opus 5
Design Arena: 3D12731334Claude Opus 5
Design Arena: all code categories12881323Claude Opus 5
Design Arena: SVG12271311Claude Opus 5
Design Arena: ASCII art12551352Claude Opus 5
LiveBench designNot measured83.0%Only Claude Opus 5 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index1119
General benchmarks for Claude Opus 4.6 and Claude Opus 5
BenchmarkClaude Opus 4.6Claude Opus 5Leader
LiveBench data analysisNot measured74.6%Only Claude Opus 5 measured
Public Benefits Bench (Vals AI)Not measured76.9%Only Claude Opus 5 measured
SAGE (Vals AI)51.6%49.4%Claude Opus 4.6
MedScribe (Vals AI)86.7%91.0%Claude Opus 5
Vals Multimodal IndexNot measured73.9%Only Claude Opus 5 measured
IFBench53.1%Not measuredOnly Claude Opus 4.6 measured
Long context reasoning (AA-LCR)78.0%82.0%Claude Opus 5
DTBench91.2%97.9%Claude Opus 5
LMCA55.8%64.5%Claude Opus 5
CL-bench20.7%Not measuredOnly Claude Opus 4.6 measured
Furniture assembly28.3%60.8%Claude Opus 5
CL-bench Life17.0%Not measuredOnly Claude Opus 4.6 measured
LMArena Text15011509Claude Opus 5
LMArena Text: instruction following15211518Claude Opus 4.6
LMArena Text: creative writing15051493Claude Opus 4.6
LMArena Vision13161320Claude Opus 5
LMArena Text: English15111508Claude Opus 4.6
LMArena Text: non-English14881502Claude Opus 5
LMArena Text: Chinese15511573Claude Opus 5
LMArena Text: German15001527Claude Opus 5
LMArena Text: Japanese14881520Claude Opus 5
LMArena Text: Korean14641517Claude Opus 5
LMArena Text: French15121519Claude Opus 5
LMArena Text: Spanish15101523Claude Opus 5
LMArena Text: Russian14971507Claude Opus 5
LMArena Text: Polish14991522Claude Opus 5
LMArena Text: multi-turn15111500Claude Opus 4.6
LMArena Text: longer queries15181517Claude Opus 4.6
LMArena Text: writing and language15021499Claude Opus 4.6
LMArena Text: entertainment and media14921481Claude Opus 4.6
LMArena Vision: English13241315Claude Opus 4.6
LMArena Vision: Chinese13701400Claude Opus 5
LMArena Vision: reading text13261329Claude Opus 5
LMArena Vision: humor13141293Claude Opus 4.6
LMArena Vision: recognizing things1274Not measuredOnly Claude Opus 4.6 measured
LMArena Vision: creative writing13311313Claude Opus 4.6
LMArena Document15071516Claude Opus 5
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 4.6 and Claude Opus 5
BenchmarkClaude Opus 4.6Claude Opus 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 4.6$0.018Fits in one request
Claude Opus 5$0.018Fits in one request

Same cost

Repository review

50K input + 3K output tokens

Claude Opus 4.6$0.325Fits in one request
Claude Opus 5$0.325Fits in one request

Same cost

Agent loop

200K input + 10K output tokens

Claude Opus 4.6$1.25Fits in one request
Claude Opus 5$1.25Fits in one request

Same cost

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 Opus 5
SpecificationAnthropic Claude Opus 4.6Anthropic Claude Opus 5
MakerAnthropicAnthropic
WeightsNo public weights listedNo public weights listed
ReleasedFebruary 4, 2026July 24, 2026
Context window1M1M
Input $/Mtok$5.00$5.00
Output $/Mtok$25.00$25.00
Coding index57.283.0
Independent measurements behind it46
Cost per solved task$1.56$1.33
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.6 better than Claude Opus 5 for coding?

Pick Claude Opus 5 for coding: it scores 83.0 on the Vibe Coding Index against 57.2 for Claude Opus 4.6. Pick Claude Opus 4.6 for work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.

Which is cheaper, Claude Opus 4.6 or Claude Opus 5?

Claude Opus 4.6 costs $5.00 per million input tokens and $25.00 per million output tokens; Claude Opus 5 costs $5.00 and $25.00. Per solved SWE-bench Verified task, Claude Opus 4.6 costs $1.56 and Claude Opus 5 $1.33.

Which has the bigger context window, Claude Opus 4.6 or Claude Opus 5?

Neither: both take 1M tokens.

How many benchmarks is the Claude Opus 4.6 vs Claude Opus 5 comparison based on?

91 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 Opus 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-4-6-vs-claude-opus-5" title="Claude Opus 4.6 vs Claude Opus 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-4-6-vs-claude-opus-5">LLMBenchmark.ai, Claude Opus 4.6 vs Claude Opus 5</a></p>