LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Opus 4.1 vs Claude Sonnet 4.6

Updated October 21, 2026. 58 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Opus 4.1 Replace Claude Sonnet 4.6
Claude Opus 4.1Anthropic
Coding
27.2
Overall
22.8
Output $/M
$75.00
4
Claude Sonnet 4.6Anthropic
Coding
57.8
Overall
30.1
Output $/M
$15.00
54
vs boards won of 58 shared

Decision reading

Pick Claude Sonnet 4.6 for coding: it scores 57.8 on the Vibe Coding Index against 27.2 for Claude Opus 4.1.

Pick Claude Opus 4.1 when what matters is Mystery game puzzles or MMLU Pro, where it leads.

Model AClaude Opus 4.1Anthropic27.2/1001 independent benchmarkNo cost per solved taskModel BClaude Sonnet 4.6Anthropic57.8/1002 independent benchmarks$1.68 per solved task
Shared results
58
Claude Opus 4.1 only
13
Claude Sonnet 4.6 only
59
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 4.1 27.2 from 1 benchmark, Claude Sonnet 4.6 57.8 from 2 benchmarks.
Widest category
Coding, 14.5 points apart on average over 7 shared benchmarks.
Widest single gap
LMArena WebDev: HTML: Claude Opus 4.1 1399 against Claude Sonnet 4.6 1527, 21.3 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.1 $75.00 against Claude Sonnet 4.6 $15.00 per million output tokens, 5.0x apart.
Context window
Claude Opus 4.1 takes 200K tokens, Claude Sonnet 4.6 1M.

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 4.1BarsClaude Sonnet 4.6Ties
Coding07
Intelligence02
Agentic work01
Reasoning16
Math04
Knowledge36
Web design08
General020
All shared boards454
CodingLike-for-likeFour of these boards feed the Vibe Coding Index07
Coding benchmarks for Claude Opus 4.1 and Claude Sonnet 4.6
BenchmarkClaude Opus 4.1Claude Sonnet 4.6Leader
LiveBench codingNot measured66.6%Only Claude Sonnet 4.6 measured
LMArena WebDev13901523Claude Sonnet 4.6
AA Coding IndexNot measured63.0Only Claude Sonnet 4.6 measured
LiveCodeBench (Vals AI)66.5%82.1%Claude Sonnet 4.6
SWE-bench Verified (Vals AI)Not measured77.4%Only Claude Sonnet 4.6 measured
Vibe Code Bench (Vals AI)Not measured55.8%Only Claude Sonnet 4.6 measured
Code migration (Vals AI)Not measured39.9%Only Claude Sonnet 4.6 measured
ProgramBench (Vals AI)Not measured0.5%Only Claude Sonnet 4.6 measured
Terminal-Bench 2.1 (Vals AI)Not measured57.3%Only Claude Sonnet 4.6 measured
SkillsBench (Vals AI)Not measured49.0%Only Claude Sonnet 4.6 measured
SciCodeNot measured50.1%Only Claude Sonnet 4.6 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured53.0%Only Claude Sonnet 4.6 measured
Terminal-Bench38.0%53.4%Claude Sonnet 4.6
FrontierCodeNot measured24.3%Only Claude Sonnet 4.6 measured
WeirdML45.9%66.1%Claude Sonnet 4.6
Cybench42.0%Not measuredOnly Claude Opus 4.1 measured
LMArena Text: coding14791503Claude Sonnet 4.6
LMArena Text: software and IT14561491Claude Sonnet 4.6
LMArena WebDev: ReactNot measured1512Only Claude Sonnet 4.6 measured
LMArena WebDev: HTML13991527Claude Sonnet 4.6
LMArena WebDev: from an imageNot measured1529Only Claude Sonnet 4.6 measured
Neither model has a result on the other 17 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Opus 4.1 and Claude Sonnet 4.6
BenchmarkClaude Opus 4.1Claude Sonnet 4.6Leader
AA Intelligence Index22.830.1Claude Sonnet 4.6
Epoch Capabilities Index144.1152.8Claude Sonnet 4.6
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Claude Opus 4.1 and Claude Sonnet 4.6
BenchmarkClaude Opus 4.1Claude Sonnet 4.6Leader
AA Agentic IndexNot measured31.8Only Claude Sonnet 4.6 measured
Design Arena: agents building web appsNot measured1190Only Claude Sonnet 4.6 measured
Design Arena: agents building full-stack appsNot measured1213Only Claude Sonnet 4.6 measured
Design Arena: agents building mobile appsNot measured1212Only Claude Sonnet 4.6 measured
Design Arena: agents building Android appsNot measured1202Only 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
LiveBench researchNot measured63.6%Only Claude Sonnet 4.6 measured
LiveBench browserNot measured68.0%Only Claude Sonnet 4.6 measured
LiveBench long agenticNot measured23.1%Only Claude Sonnet 4.6 measured
Finance Agent (Vals AI)Not measured51.0%Only Claude Sonnet 4.6 measured
Tax Agent Bench (Vals AI)Not measured25.8%Only Claude Sonnet 4.6 measured
Legal Research Bench (Vals AI)Not measured38.5%Only Claude Sonnet 4.6 measured
Excel Modeling Benchmark (Vals AI)Not measured60.2%Only Claude Sonnet 4.6 measured
τ²-Bench TelecomNot measured79.5%Only Claude Sonnet 4.6 measured
APEX-AgentsNot measured43.0%Only Claude Sonnet 4.6 measured
METR time horizons66.8%Not measuredOnly Claude Opus 4.1 measured
GDPval43.6%Not measuredOnly Claude Opus 4.1 measured
OSWorld 2.0Not measured9.3%Only Claude Sonnet 4.6 measured
DeepResearch Bench48.3%54.9%Claude Sonnet 4.6
OSWorldNot measured72.1%Only Claude Sonnet 4.6 measured
Vending-Bench 2Not measured$7,204Only Claude Sonnet 4.6 measured
Neither model has a result on the other 17 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index16
Reasoning benchmarks for Claude Opus 4.1 and Claude Sonnet 4.6
BenchmarkClaude Opus 4.1Claude Sonnet 4.6Leader
GPQA Diamond76.3%85.6%Claude Sonnet 4.6
LiveBench reasoningNot measured86.4%Only Claude Sonnet 4.6 measured
MMMU Pro (Vals AI)77.5%83.6%Claude Sonnet 4.6
GPQA Diamond (Artificial Analysis run)Not measured87.5%Only Claude Sonnet 4.6 measured
Humanity's Last Exam (Artificial Analysis run)Not measured33.6%Only Claude Sonnet 4.6 measured
GPQA Diamond (Epoch AI run)77.3%87.4%Claude Sonnet 4.6
ARC-AGINot measured86.5%Only Claude Sonnet 4.6 measured
ARC-AGI-2Not measured60.4%Only Claude Sonnet 4.6 measured
SimpleBench60.0%Not measuredOnly Claude Opus 4.1 measured
Chess puzzlesNot measured23.0%Only Claude Sonnet 4.6 measured
Mystery game puzzles21.0%16.0%Claude Opus 4.1
EBR-bench7.9%Not measuredOnly Claude Opus 4.1 measured
VPCT35.0%Not measuredOnly Claude Opus 4.1 measured
LMArena Text: hard prompts14421485Claude Sonnet 4.6
LMArena Text: expert14381500Claude Sonnet 4.6
LMArena Text: hard prompts in English14511493Claude Sonnet 4.6
LMArena Vision: diagramsNot measured1306Only Claude Sonnet 4.6 measured
LMArena Vision: homeworkNot measured1311Only Claude Sonnet 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 index04
Math benchmarks for Claude Opus 4.1 and Claude Sonnet 4.6
BenchmarkClaude Opus 4.1Claude Sonnet 4.6Leader
AIME78.2%92.3%Claude Sonnet 4.6
MATH 500 (Vals AI)95.4%Not measuredOnly Claude Opus 4.1 measured
MGSM (Vals AI)94.4%Not measuredOnly Claude Opus 4.1 measured
OTIS Mock AIME68.9%85.8%Claude Sonnet 4.6
FrontierMath, tiers 1 to 312.6%Not measuredOnly Claude Opus 4.1 measured
FrontierMath, tier 42.4%Not measuredOnly Claude Opus 4.1 measured
ProofBenchNot measured45.0%Only Claude Sonnet 4.6 measured
LMArena Text: math14311462Claude Sonnet 4.6
LMArena Text: mathematical work14341483Claude Sonnet 4.6
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index36
Knowledge benchmarks for Claude Opus 4.1 and Claude Sonnet 4.6
BenchmarkClaude Opus 4.1Claude Sonnet 4.6Leader
MMLU Pro87.9%87.3%Claude Opus 4.1
LegalBench (Vals AI)83.5%82.1%Claude Opus 4.1
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)73.7%77.1%Claude Sonnet 4.6
MortgageTax (Vals AI)61.1%67.7%Claude Sonnet 4.6
MedQA (Vals AI)93.6%92.1%Claude Opus 4.1
MedCode (Vals AI)47.2%Not measuredOnly Claude Opus 4.1 measured
SimpleQA VerifiedNot measured35.5%Only Claude Sonnet 4.6 measured
LMArena Text: science14221474Claude Sonnet 4.6
LMArena Text: medicine and healthcare14161451Claude Sonnet 4.6
LMArena Text: legal and government14211470Claude Sonnet 4.6
LMArena Text: business and finance14061464Claude Sonnet 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 index08
Web design benchmarks for Claude Opus 4.1 and Claude Sonnet 4.6
BenchmarkClaude Opus 4.1Claude Sonnet 4.6Leader
Design Arena: websites11771285Claude Sonnet 4.6
Design Arena: UI components11641271Claude Sonnet 4.6
Design Arena: game dev11721259Claude Sonnet 4.6
Design Arena: data viz11661278Claude Sonnet 4.6
Design Arena: 3D11531234Claude Sonnet 4.6
Design Arena: all code categories11711276Claude Sonnet 4.6
Design Arena: SVG11521196Claude Sonnet 4.6
Design Arena: ASCII art11671235Claude Sonnet 4.6
LiveBench designNot measured71.8%Only Claude Sonnet 4.6 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index020
General benchmarks for Claude Opus 4.1 and Claude Sonnet 4.6
BenchmarkClaude Opus 4.1Claude Sonnet 4.6Leader
LiveBench data analysisNot measured76.1%Only Claude Sonnet 4.6 measured
Public Benefits Bench (Vals AI)Not measured62.5%Only Claude Sonnet 4.6 measured
SAGE (Vals AI)31.4%46.6%Claude Sonnet 4.6
MedScribe (Vals AI)73.9%Not measuredOnly Claude Opus 4.1 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)Not measured80.0%Only Claude Sonnet 4.6 measured
DTBench80.0%89.9%Claude Sonnet 4.6
LMCA37.1%46.5%Claude Sonnet 4.6
Creative writing (Lech Mazur)84.7%Not measuredOnly Claude Opus 4.1 measured
ExploitBenchNot measured23.6%Only Claude Sonnet 4.6 measured
LMArena Text14191458Claude Sonnet 4.6
LMArena Text: instruction following14351476Claude Sonnet 4.6
LMArena Text: creative writing14121435Claude Sonnet 4.6
LMArena VisionNot measured1283Only Claude Sonnet 4.6 measured
LMArena Text: English14331472Claude Sonnet 4.6
LMArena Text: non-English14051440Claude Sonnet 4.6
LMArena Text: Chinese14271491Claude Sonnet 4.6
LMArena Text: German14131428Claude Sonnet 4.6
LMArena Text: Japanese13771420Claude Sonnet 4.6
LMArena Text: Korean13811410Claude Sonnet 4.6
LMArena Text: French14331465Claude Sonnet 4.6
LMArena Text: Spanish14481464Claude Sonnet 4.6
LMArena Text: Russian14221440Claude Sonnet 4.6
LMArena Text: Polish14131443Claude Sonnet 4.6
LMArena Text: multi-turn14441464Claude Sonnet 4.6
LMArena Text: longer queries14551479Claude Sonnet 4.6
LMArena Text: writing and language14181444Claude Sonnet 4.6
LMArena Text: entertainment and media13981431Claude Sonnet 4.6
LMArena Vision: EnglishNot measured1298Only Claude Sonnet 4.6 measured
LMArena Vision: ChineseNot measured1307Only Claude Sonnet 4.6 measured
LMArena Vision: reading textNot measured1296Only Claude Sonnet 4.6 measured
LMArena Vision: humorNot measured1248Only Claude Sonnet 4.6 measured
LMArena Vision: recognizing thingsNot measured1195Only Claude Sonnet 4.6 measured
LMArena Vision: creative writingNot measured1272Only Claude Sonnet 4.6 measured
LMArena DocumentNot measured1482Only Claude Sonnet 4.6 measured
Neither model has a result on the other 10 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Opus 4.1 and Claude Sonnet 4.6
BenchmarkClaude Opus 4.1Claude 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 4.1$0.052Fits 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 4.1$0.975Fits 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 4.1$3.75Exceeds the context window
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 4.1 and Claude Sonnet 4.6
SpecificationAnthropic Claude Opus 4.1Anthropic Claude Sonnet 4.6
MakerAnthropicAnthropic
WeightsNo public weights listedNo public weights listed
ReleasedAugust 5, 2025February 17, 2026
Context window200K1M
Input $/Mtok$15.00$3.00
Output $/Mtok$75.00$15.00
Coding index27.257.8
Independent measurements behind it12
Cost per solved taskNot computable$1.68
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.1 better than Claude Sonnet 4.6 for coding?

Pick Claude Sonnet 4.6 for coding: it scores 57.8 on the Vibe Coding Index against 27.2 for Claude Opus 4.1. Pick Claude Opus 4.1 when what matters is Mystery game puzzles or MMLU Pro, where it leads.

Which is cheaper, Claude Opus 4.1 or Claude Sonnet 4.6?

Claude Opus 4.1 costs $15.00 per million input tokens and $75.00 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 4.1 or Claude Sonnet 4.6?

Claude Sonnet 4.6, with 1M tokens against 200K.

How many benchmarks is the Claude Opus 4.1 vs Claude Sonnet 4.6 comparison based on?

58 benchmarks have a result for both models as of October 21, 2026. Claude Opus 4.1's coding index rests on 1 independent benchmark and Claude Sonnet 4.6's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next