LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Opus 4.1 vs Claude Sonnet 4.5

Updated October 21, 2026. 69 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 4.5
Claude Opus 4.1Anthropic
Coding
27.2
Overall
22.8
Output $/M
$75.00
11
Claude Sonnet 4.5Anthropic
Coding
59.1
Overall
20.7
Output $/M
$15.00
57
vs boards won of 69 shared, 1 tied

Decision reading

Pick Claude Sonnet 4.5 for coding: it scores 59.1 on the Vibe Coding Index against 27.2 for Claude Opus 4.1.

Pick Claude Opus 4.1 when what matters is AA Intelligence Index or GDPval, where it leads.

Model AClaude Opus 4.1Anthropic27.2/1001 independent benchmarkNo cost per solved taskModel BClaude Sonnet 4.5Anthropic59.1/1002 independent benchmarks$1.16 per solved task
Shared results
69
Claude Opus 4.1 only
2
Claude Sonnet 4.5 only
23
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 4.5 59.1 from 2 benchmarks.
Widest category
Math, 5.4 points apart on average over 7 shared benchmarks.
Widest single gap
Cybench: Claude Opus 4.1 42.0% against Claude Sonnet 4.5 60.0%, 18.0 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.1 $75.00 against Claude Sonnet 4.5 $15.00 per million output tokens, 5.0x apart.
Context window
Claude Opus 4.1 takes 200K tokens, Claude Sonnet 4.5 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 4.5Ties
Coding08
Intelligence11
Agentic work12
Reasoning37
Math151 tie
Knowledge37
Web design26
General021
All shared boards11571 tie
CodingLike-for-likeFour of these boards feed the Vibe Coding Index08
Coding benchmarks for Claude Opus 4.1 and Claude Sonnet 4.5
BenchmarkClaude Opus 4.1Claude Sonnet 4.5Leader
SWE-bench VerifiedNot measured74.8%Only Claude Sonnet 4.5 measured
SWE-bench MultilingualNot measured67.0%Only Claude Sonnet 4.5 measured
LMArena WebDev13901394Claude Sonnet 4.5
AA Coding IndexNot measured52.1Only Claude Sonnet 4.5 measured
LiveCodeBench (Vals AI)66.5%73.0%Claude Sonnet 4.5
SWE-bench Verified (Vals AI)Not measured70.0%Only Claude Sonnet 4.5 measured
Vibe Code Bench (Vals AI)Not measured22.6%Only Claude Sonnet 4.5 measured
Terminal-Bench38.0%46.5%Claude Sonnet 4.5
GSO-BenchNot measured14.7%Only Claude Sonnet 4.5 measured
WeirdML45.9%47.7%Claude Sonnet 4.5
Cybench42.0%60.0%Claude Sonnet 4.5
LMArena Text: coding14791488Claude Sonnet 4.5
LMArena Text: software and IT14561473Claude Sonnet 4.5
LMArena WebDev: ReactNot measured1386Only Claude Sonnet 4.5 measured
LMArena WebDev: HTML13991399Claude Sonnet 4.5
Neither model has a result on the other 23 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
Intelligence benchmarks for Claude Opus 4.1 and Claude Sonnet 4.5
BenchmarkClaude Opus 4.1Claude Sonnet 4.5Leader
AA Intelligence Index22.820.7Claude Opus 4.1
Epoch Capabilities Index144.1146.7Claude Sonnet 4.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index12
Agentic work benchmarks for Claude Opus 4.1 and Claude Sonnet 4.5
BenchmarkClaude Opus 4.1Claude Sonnet 4.5Leader
AA Agentic IndexNot measured15.8Only Claude Sonnet 4.5 measured
Design Arena: agents building web appsNot measured1060Only Claude Sonnet 4.5 measured
Design Arena: agents building full-stack appsNot measured1050Only Claude Sonnet 4.5 measured
Design Arena: agents building mobile appsNot measured1137Only Claude Sonnet 4.5 measured
METR time horizons66.8%67.4%Claude Sonnet 4.5
Remote Labor IndexNot measured2.1%Only Claude Sonnet 4.5 measured
GDPval43.6%42.5%Claude Opus 4.1
DeepResearch Bench48.3%52.6%Claude Sonnet 4.5
OSWorldNot measured62.9%Only Claude Sonnet 4.5 measured
Vending-Bench 2Not measured$3,839Only Claude Sonnet 4.5 measured
Neither model has a result on the other 29 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index37
Reasoning benchmarks for Claude Opus 4.1 and Claude Sonnet 4.5
BenchmarkClaude Opus 4.1Claude Sonnet 4.5Leader
GPQA Diamond76.3%81.6%Claude Sonnet 4.5
MMMU Pro (Vals AI)77.5%79.3%Claude Sonnet 4.5
GPQA Diamond (Epoch AI run)77.3%82.3%Claude Sonnet 4.5
ARC-AGINot measured63.7%Only Claude Sonnet 4.5 measured
ARC-AGI-2Not measured13.6%Only Claude Sonnet 4.5 measured
SimpleBench60.0%54.3%Claude Opus 4.1
Chess puzzlesNot measured10.0%Only Claude Sonnet 4.5 measured
Mystery game puzzles21.0%17.0%Claude Opus 4.1
EBR-bench7.9%2.4%Claude Opus 4.1
VPCT35.0%39.8%Claude Sonnet 4.5
LMArena Text: hard prompts14421462Claude Sonnet 4.5
LMArena Text: expert14381483Claude Sonnet 4.5
LMArena Text: hard prompts in English14511471Claude Sonnet 4.5
Neither model has a result on the other 8 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index15
Math benchmarks for Claude Opus 4.1 and Claude Sonnet 4.5
BenchmarkClaude Opus 4.1Claude Sonnet 4.5Leader
AIME78.2%88.2%Claude Sonnet 4.5
MATH 500 (Vals AI)95.4%Not measuredOnly Claude Opus 4.1 measured
MGSM (Vals AI)94.4%94.3%Claude Opus 4.1
OTIS Mock AIME68.9%77.8%Claude Sonnet 4.5
FrontierMath, tiers 1 to 312.6%23.9%Claude Sonnet 4.5
FrontierMath, tier 42.4%2.4%Tie
ProofBenchNot measured19.0%Only Claude Sonnet 4.5 measured
MATH level 5Not measured97.7%Only Claude Sonnet 4.5 measured
LMArena Text: math14311449Claude Sonnet 4.5
LMArena Text: mathematical work14341462Claude Sonnet 4.5
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index37
Knowledge benchmarks for Claude Opus 4.1 and Claude Sonnet 4.5
BenchmarkClaude Opus 4.1Claude Sonnet 4.5Leader
MMLU Pro87.9%87.4%Claude Opus 4.1
LegalBench (Vals AI)83.5%84.1%Claude Sonnet 4.5
CaseLaw (Vals AI)Not measured62.2%Only Claude Sonnet 4.5 measured
CorpFin (Vals AI)Not measured62.0%Only Claude Sonnet 4.5 measured
TaxEval (Vals AI)73.7%73.3%Claude Opus 4.1
MortgageTax (Vals AI)61.1%64.0%Claude Sonnet 4.5
MedQA (Vals AI)93.6%94.7%Claude Sonnet 4.5
MedCode (Vals AI)47.2%44.1%Claude Opus 4.1
SimpleQA VerifiedNot measured30.7%Only Claude Sonnet 4.5 measured
LMArena Text: science14221448Claude Sonnet 4.5
LMArena Text: medicine and healthcare14161444Claude Sonnet 4.5
LMArena Text: legal and government14211451Claude Sonnet 4.5
LMArena Text: business and finance14061440Claude Sonnet 4.5
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index26
Web design benchmarks for Claude Opus 4.1 and Claude Sonnet 4.5
BenchmarkClaude Opus 4.1Claude Sonnet 4.5Leader
Design Arena: websites11771190Claude Sonnet 4.5
Design Arena: UI components11641173Claude Sonnet 4.5
Design Arena: game dev11721166Claude Opus 4.1
Design Arena: data viz11661167Claude Sonnet 4.5
Design Arena: 3D11531158Claude Sonnet 4.5
Design Arena: all code categories11711183Claude Sonnet 4.5
Design Arena: SVG11521114Claude Opus 4.1
Design Arena: ASCII art11671204Claude Sonnet 4.5
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index021
General benchmarks for Claude Opus 4.1 and Claude Sonnet 4.5
BenchmarkClaude Opus 4.1Claude Sonnet 4.5Leader
SAGE (Vals AI)31.4%36.1%Claude Sonnet 4.5
MedScribe (Vals AI)73.9%84.5%Claude Sonnet 4.5
DTBench80.0%83.2%Claude Sonnet 4.5
LMCA37.1%38.8%Claude Sonnet 4.5
Creative writing (Lech Mazur)84.7%Not measuredOnly Claude Opus 4.1 measured
LMArena Text14191438Claude Sonnet 4.5
LMArena Text: instruction following14351459Claude Sonnet 4.5
LMArena Text: creative writing14121442Claude Sonnet 4.5
LMArena Text: English14331450Claude Sonnet 4.5
LMArena Text: non-English14051425Claude Sonnet 4.5
LMArena Text: Chinese14271460Claude Sonnet 4.5
LMArena Text: German14131427Claude Sonnet 4.5
LMArena Text: Japanese13771390Claude Sonnet 4.5
LMArena Text: Korean13811402Claude Sonnet 4.5
LMArena Text: French14331459Claude Sonnet 4.5
LMArena Text: Spanish14481458Claude Sonnet 4.5
LMArena Text: Russian14221437Claude Sonnet 4.5
LMArena Text: Polish14131423Claude Sonnet 4.5
LMArena Text: multi-turn14441465Claude Sonnet 4.5
LMArena Text: longer queries14551475Claude Sonnet 4.5
LMArena Text: writing and language14181442Claude Sonnet 4.5
LMArena Text: entertainment and media13981428Claude Sonnet 4.5
LMArena DocumentNot measured1450Only Claude Sonnet 4.5 measured
Neither model has a result on the other 23 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 4.5
BenchmarkClaude Opus 4.1Claude 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 4.1$0.052Fits 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 4.1$0.975Fits 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 4.1$3.75Exceeds the context window
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 4.1 and Claude Sonnet 4.5
SpecificationAnthropic Claude Opus 4.1Anthropic Claude Sonnet 4.5
MakerAnthropicAnthropic
WeightsNo public weights listedNo public weights listed
ReleasedAugust 5, 2025September 29, 2025
Context window200K1M
Input $/Mtok$15.00$3.00
Output $/Mtok$75.00$15.00
Coding index27.259.1
Independent measurements behind it12
Cost per solved taskNot computable$1.16
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.1 better than Claude Sonnet 4.5 for coding?

Pick Claude Sonnet 4.5 for coding: it scores 59.1 on the Vibe Coding Index against 27.2 for Claude Opus 4.1. Pick Claude Opus 4.1 when what matters is AA Intelligence Index or GDPval, where it leads.

Which is cheaper, Claude Opus 4.1 or Claude Sonnet 4.5?

Claude Opus 4.1 costs $15.00 per million input tokens and $75.00 per million output tokens; Claude Sonnet 4.5 costs $3.00 and $15.00. Cost per solved task is known for Claude Sonnet 4.5 only.

Which has the bigger context window, Claude Opus 4.1 or Claude Sonnet 4.5?

Claude Sonnet 4.5, with 1M tokens against 200K.

How many benchmarks is the Claude Opus 4.1 vs Claude Sonnet 4.5 comparison based on?

69 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 4.5's on 2. Where only one model has a result, the page says so instead of naming a winner.

Compare next