Enter opens the highlighted result. Esc closes.

Claude Opus 4.6 vs Claude Sonnet 4.5

Updated October 21, 2026. 85 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Opus 4.6 Replace Claude Sonnet 4.5
Claude Opus 4.6Anthropic
Coding
66.9
Overall
31.9
Output $/M
$25.00
84
Claude Sonnet 4.5Anthropic
Coding
59.1
Overall
20.7
Output $/M
$15.00
1
vs boards won of 85 shared

Decision reading

Pick Claude Opus 4.6 for coding: it scores 66.9 on the Vibe Coding Index against 59.1 for Claude Sonnet 4.5.

Pick Claude Sonnet 4.5 when output tokens cost 1.7x less, or when a solved task costs $1.16 against $1.56.

Model AClaude Opus 4.6Anthropic66.9/1002 independent benchmarks$1.56 per solved taskModel BClaude Sonnet 4.5Anthropic59.1/1002 independent benchmarks$1.16 per solved task
Shared results
85
Claude Opus 4.6 only
23
Claude Sonnet 4.5 only
7
Like-for-like categories
8 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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 66.9 from 2 benchmarks, Claude Sonnet 4.5 59.1 from 2 benchmarks.
Widest category
Math, 20.5 points apart on average over 7 shared benchmarks.
Widest single gap
ARC-AGI-2: Claude Opus 4.6 69.2% against Claude Sonnet 4.5 13.6%, 55.6 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.6 $25.00 against Claude Sonnet 4.5 $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 4.5Ties
Coding140
Intelligence20
Agentic work70
Reasoning120
Math70
Knowledge121
Web design80
General220
All shared boards841
CodingLike-for-likeFour of these boards feed the Vibe Coding Index140
Coding benchmarks for Claude Opus 4.6 and Claude Sonnet 4.5
BenchmarkClaude Opus 4.6Claude Sonnet 4.5Leader
SWE-bench Verified75.6%74.8%Claude Opus 4.6
SWE-bench Multilingual72.0%67.0%Claude Opus 4.6
LMArena WebDev15471394Claude Opus 4.6
AA Coding IndexNot measured52.1Only Claude Sonnet 4.5 measured
LiveCodeBench (Vals AI)84.7%73.0%Claude Opus 4.6
SWE-bench Verified (Vals AI)78.2%70.0%Claude Opus 4.6
Vibe Code Bench (Vals AI)57.6%22.6%Claude Opus 4.6
Terminal-Bench Hard (Artificial Analysis run)48.5%Not measuredOnly Claude Opus 4.6 measured
Terminal-Bench79.8%46.5%Claude Opus 4.6
FrontierCode26.6%Not measuredOnly Claude Opus 4.6 measured
GSO-Bench41.2%14.7%Claude Opus 4.6
WeirdML78.0%47.7%Claude Opus 4.6
Cybench93.0%60.0%Claude Opus 4.6
LMArena Text: coding15341488Claude Opus 4.6
LMArena Text: software and IT15271473Claude Opus 4.6
LMArena WebDev: React15391386Claude Opus 4.6
LMArena WebDev: HTML15591399Claude Opus 4.6
LMArena WebDev: from an image1543Not measuredOnly Claude Opus 4.6 measured
Neither model has a result on the other 20 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Opus 4.6 and Claude Sonnet 4.5
BenchmarkClaude Opus 4.6Claude Sonnet 4.5Leader
AA Intelligence Index31.920.7Claude Opus 4.6
Epoch Capabilities Index155.7146.7Claude Opus 4.6
Agentic workLike-for-likePublic boards, shown as published, kept out of the index70
Agentic work benchmarks for Claude Opus 4.6 and Claude Sonnet 4.5
BenchmarkClaude Opus 4.6Claude Sonnet 4.5Leader
AA Agentic IndexNot measured15.8Only Claude Sonnet 4.5 measured
Design Arena: agents building web apps12061060Claude Opus 4.6
Design Arena: agents building full-stack apps12201050Claude Opus 4.6
Design Arena: agents building mobile apps12071137Claude Opus 4.6
Design Arena: agents building Android apps1204Not measuredOnly Claude Opus 4.6 measured
Design Arena: agents building games1214Not measuredOnly Claude Opus 4.6 measured
τ²-Bench Telecom92.1%Not measuredOnly Claude Opus 4.6 measured
APEX-Agents46.3%Not measuredOnly Claude Opus 4.6 measured
METR time horizons78.9%67.4%Claude Opus 4.6
Remote Labor Index4.2%2.1%Claude Opus 4.6
GDPvalNot measured42.5%Only Claude Sonnet 4.5 measured
DeepResearch Bench55.3%52.6%Claude Opus 4.6
OSWorldNot measured62.9%Only Claude Sonnet 4.5 measured
Vending-Bench 2$8,018$3,839Claude Opus 4.6
Neither model has a result on the other 25 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index120
Reasoning benchmarks for Claude Opus 4.6 and Claude Sonnet 4.5
BenchmarkClaude Opus 4.6Claude Sonnet 4.5Leader
GPQA Diamond89.7%81.6%Claude Opus 4.6
MMMU Pro (Vals AI)83.9%79.3%Claude Opus 4.6
GPQA Diamond (Artificial Analysis run)89.6%Not measuredOnly Claude Opus 4.6 measured
Humanity's Last Exam (Artificial Analysis run)39.9%Not measuredOnly Claude Opus 4.6 measured
GPQA Diamond (Epoch AI run)90.5%82.3%Claude Opus 4.6
ARC-AGI94.0%63.7%Claude Opus 4.6
ARC-AGI-269.2%13.6%Claude Opus 4.6
SimpleBench67.6%54.3%Claude Opus 4.6
Chess puzzles21.0%10.0%Claude Opus 4.6
Mystery game puzzles25.0%17.0%Claude Opus 4.6
EBR-bench12.7%2.4%Claude Opus 4.6
VPCTNot measured39.8%Only Claude Sonnet 4.5 measured
LMArena Text: hard prompts15251462Claude Opus 4.6
LMArena Text: expert15441483Claude Opus 4.6
LMArena Text: hard prompts in English15301471Claude Opus 4.6
LMArena Vision: diagrams1340Not measuredOnly Claude Opus 4.6 measured
LMArena Vision: homework1337Not 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 index70
Math benchmarks for Claude Opus 4.6 and Claude Sonnet 4.5
BenchmarkClaude Opus 4.6Claude Sonnet 4.5Leader
AIME95.6%88.2%Claude Opus 4.6
MGSM (Vals AI)Not measured94.3%Only Claude Sonnet 4.5 measured
OTIS Mock AIME94.4%77.8%Claude Opus 4.6
FrontierMath, tiers 1 to 366.0%23.9%Claude Opus 4.6
FrontierMath, tier 426.8%2.4%Claude Opus 4.6
ProofBench50.0%19.0%Claude Opus 4.6
MATH level 5Not measured97.7%Only Claude Sonnet 4.5 measured
LMArena Text: math15181449Claude Opus 4.6
LMArena Text: mathematical work15251462Claude Opus 4.6
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index121
Knowledge benchmarks for Claude Opus 4.6 and Claude Sonnet 4.5
BenchmarkClaude Opus 4.6Claude Sonnet 4.5Leader
MMLU Pro89.1%87.4%Claude Opus 4.6
LegalBench (Vals AI)85.3%84.1%Claude Opus 4.6
CaseLaw (Vals AI)62.1%62.2%Claude Sonnet 4.5
CorpFin (Vals AI)67.0%62.0%Claude Opus 4.6
TaxEval (Vals AI)76.0%73.3%Claude Opus 4.6
MortgageTax (Vals AI)68.5%64.0%Claude Opus 4.6
MedQA (Vals AI)95.4%94.7%Claude Opus 4.6
MedCode (Vals AI)49.1%44.1%Claude Opus 4.6
SimpleQA Verified47.0%30.7%Claude Opus 4.6
LMArena Text: science15191448Claude Opus 4.6
LMArena Text: medicine and healthcare15041444Claude Opus 4.6
LMArena Text: legal and government15121451Claude Opus 4.6
LMArena Text: business and finance14971440Claude 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 4.5
BenchmarkClaude Opus 4.6Claude Sonnet 4.5Leader
Design Arena: websites12911190Claude Opus 4.6
Design Arena: UI components12841173Claude Opus 4.6
Design Arena: game dev12781166Claude Opus 4.6
Design Arena: data viz12791167Claude Opus 4.6
Design Arena: 3D12741158Claude Opus 4.6
Design Arena: all code categories12891183Claude Opus 4.6
Design Arena: SVG12271114Claude Opus 4.6
Design Arena: ASCII art12541204Claude Opus 4.6
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index220
General benchmarks for Claude Opus 4.6 and Claude Sonnet 4.5
BenchmarkClaude Opus 4.6Claude Sonnet 4.5Leader
SAGE (Vals AI)51.6%36.1%Claude Opus 4.6
MedScribe (Vals AI)86.7%84.5%Claude Opus 4.6
IFBench53.1%Not measuredOnly Claude Opus 4.6 measured
Long context reasoning (AA-LCR)78.0%Not measuredOnly Claude Opus 4.6 measured
DTBench91.2%83.2%Claude Opus 4.6
LMCA55.8%38.8%Claude Opus 4.6
CL-bench20.7%Not measuredOnly Claude Opus 4.6 measured
Furniture assembly28.3%Not measuredOnly Claude Opus 4.6 measured
CL-bench Life17.0%Not measuredOnly Claude Opus 4.6 measured
LMArena Text15011438Claude Opus 4.6
LMArena Text: instruction following15211459Claude Opus 4.6
LMArena Text: creative writing15051442Claude Opus 4.6
LMArena Vision1316Not measuredOnly Claude Opus 4.6 measured
LMArena Text: English15111450Claude Opus 4.6
LMArena Text: non-English14881425Claude Opus 4.6
LMArena Text: Chinese15511460Claude Opus 4.6
LMArena Text: German15001427Claude Opus 4.6
LMArena Text: Japanese14881390Claude Opus 4.6
LMArena Text: Korean14641402Claude Opus 4.6
LMArena Text: French15121459Claude Opus 4.6
LMArena Text: Spanish15101458Claude Opus 4.6
LMArena Text: Russian14971437Claude Opus 4.6
LMArena Text: Polish14991423Claude Opus 4.6
LMArena Text: multi-turn15111465Claude Opus 4.6
LMArena Text: longer queries15181475Claude Opus 4.6
LMArena Text: writing and language15021442Claude Opus 4.6
LMArena Text: entertainment and media14921428Claude Opus 4.6
LMArena Vision: English1324Not measuredOnly Claude Opus 4.6 measured
LMArena Vision: Chinese1370Not measuredOnly Claude Opus 4.6 measured
LMArena Vision: reading text1326Not measuredOnly Claude Opus 4.6 measured
LMArena Vision: humor1314Not measuredOnly Claude Opus 4.6 measured
LMArena Vision: recognizing things1274Not measuredOnly Claude Opus 4.6 measured
LMArena Vision: creative writing1331Not measuredOnly Claude Opus 4.6 measured
LMArena Document15071450Claude Opus 4.6
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 4.6 and Claude Sonnet 4.5
BenchmarkClaude Opus 4.6Claude Sonnet 4.5Leader
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 Sonnet 4.5$0.011Fits in one request

Claude Sonnet 4.5 costs less

Repository review

50K input + 3K output tokens

Claude Opus 4.6$0.325Fits in one request
Claude Sonnet 4.5$0.195Fits in one request

Claude Sonnet 4.5 costs less

Agent loop

200K input + 10K output tokens

Claude Opus 4.6$1.25Fits in one request
Claude Sonnet 4.5$0.750Fits in one request

Claude Sonnet 4.5 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 4.6 and Claude Sonnet 4.5
SpecificationAnthropic Claude Opus 4.6Anthropic Claude Sonnet 4.5
MakerAnthropicAnthropic
WeightsNo public weights listedNo public weights listed
ReleasedFebruary 4, 2026September 29, 2025
Context window1M1M
Input $/Mtok$5.00$3.00
Output $/Mtok$25.00$15.00
Coding index66.959.1
Independent measurements behind it22
Cost per solved task$1.56$1.16
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.6 better than Claude Sonnet 4.5 for coding?

Pick Claude Opus 4.6 for coding: it scores 66.9 on the Vibe Coding Index against 59.1 for Claude Sonnet 4.5. Pick Claude Sonnet 4.5 when output tokens cost 1.7x less, or when a solved task costs $1.16 against $1.56.

Which is cheaper, Claude Opus 4.6 or Claude Sonnet 4.5?

Claude Opus 4.6 costs $5.00 per million input tokens and $25.00 per million output tokens; Claude Sonnet 4.5 costs $3.00 and $15.00. Per solved SWE-bench Verified task, Claude Opus 4.6 costs $1.56 and Claude Sonnet 4.5 $1.16.

Which has the bigger context window, Claude Opus 4.6 or Claude Sonnet 4.5?

Neither: both take 1M tokens.

How many benchmarks is the Claude Opus 4.6 vs Claude Sonnet 4.5 comparison based on?

85 benchmarks have a result for both models as of October 21, 2026. Claude Opus 4.6's coding index rests on 2 independent benchmarks and Claude Sonnet 4.5's on 2. 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-4-5" title="Claude Opus 4.6 vs Claude Sonnet 4.5, 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-sonnet-4-5">LLMBenchmark.ai, Claude Opus 4.6 vs Claude Sonnet 4.5</a></p>