Enter opens the highlighted result. Esc closes.

Claude Opus 4.5 vs Claude Sonnet 4.5

Claude Opus 4.5 leads Claude Sonnet 4.5 on coding, 44.0 to 39.5 on the Vibe Coding Index, and Claude Sonnet 4.5 costs 1.7x less per output token ($15.00 vs $25.00 per million). Updated October 22, 2026; 92 benchmarks have a result for both.

Replace Claude Opus 4.5 Replace Claude Sonnet 4.5
Claude Opus 4.5Anthropic
Coding
44.0
Overall
55.7
Output $/M
$25.00
87
Claude Sonnet 4.5Anthropic
Coding
39.5
Overall
49.5
Output $/M
$15.00
5
vs boards won of 92 shared

Claude Opus 4.5 or Claude Sonnet 4.5: which to pick

Pick Claude Opus 4.5 for coding: it scores 44.0 on the Vibe Coding Index against 39.5 for Claude Sonnet 4.5.

Pick Claude Sonnet 4.5 for output tokens 1.7x cheaper ($15.00 vs $25.00 per million) and a lower cost per solved task ($1.16 against $1.37).

Model AClaude Opus 4.5Anthropic44.0/1003 independent benchmarks$1.37 per solved taskModel BClaude Sonnet 4.5Anthropic39.5/1003 independent benchmarks$1.16 per solved task
Shared results
92
Claude Opus 4.5 only
16
Claude Sonnet 4.5 only
3
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 4.5 44.0 from 3 benchmarks, Claude Sonnet 4.5 39.5 from 3 benchmarks.
Widest category
Coding, 10.4 points apart on average over 14 shared benchmarks.
Widest single gap
ARC-AGI-2: Claude Opus 4.5 37.6% against Claude Sonnet 4.5 13.6%, 24.0 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.5 $25.00 against Claude Sonnet 4.5 $15.00 per million output tokens, 1.7x apart.
Context window
Claude Opus 4.5 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 4.5BarsClaude Sonnet 4.5Ties
Coding131
Intelligence20
Agentic work100
Reasoning140
Math80
Knowledge122
Web design71
General211
All shared boards875
CodingLike-for-likeSix of these boards feed the Vibe Coding Index131
Coding benchmarks for Claude Opus 4.5 and Claude Sonnet 4.5
BenchmarkClaude Opus 4.5Claude Sonnet 4.5Leader
SWE-bench Verified79.2%74.8%Claude Opus 4.5
SWE-bench (full test set)52.6%Not measuredOnly Claude Opus 4.5 measured
SWE-bench Multilingual70.7%67.0%Claude Opus 4.5
LMArena WebDev14941394Claude Opus 4.5
AA Coding IndexNot measured52.1Only Claude Sonnet 4.5 measured
LiveCodeBench (Vals AI)83.7%73.0%Claude Opus 4.5
SWE-bench Verified (Vals AI)76.4%70.0%Claude Opus 4.5
Vibe Code Bench (Vals AI)20.6%22.6%Claude Sonnet 4.5
LiveCodeBench (Artificial Analysis run)87.1%Not measuredOnly Claude Opus 4.5 measured
Terminal-Bench Hard (Artificial Analysis run)47.0%Not measuredOnly Claude Opus 4.5 measured
Terminal-Bench63.1%46.5%Claude Opus 4.5
GSO-Bench26.5%14.7%Claude Opus 4.5
WeirdML63.7%47.7%Claude Opus 4.5
Cybench82.0%60.0%Claude Opus 4.5
LMArena Text: coding15031488Claude Opus 4.5
LMArena Text: software and IT14831473Claude Opus 4.5
LMArena WebDev: React14781386Claude Opus 4.5
LMArena WebDev: HTML15101399Claude Opus 4.5
Neither model has a result on the other 21 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Opus 4.5 and Claude Sonnet 4.5
BenchmarkClaude Opus 4.5Claude Sonnet 4.5Leader
AA Intelligence Index29.120.7Claude Opus 4.5
Epoch Capabilities Index150.1146.7Claude Opus 4.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index100
Agentic work benchmarks for Claude Opus 4.5 and Claude Sonnet 4.5
BenchmarkClaude Opus 4.5Claude Sonnet 4.5Leader
AA Agentic IndexNot measured15.8Only Claude Sonnet 4.5 measured
Design Arena: agents building web apps11591060Claude Opus 4.5
Design Arena: agents building full-stack apps11561050Claude Opus 4.5
Design Arena: agents building mobile apps11891137Claude Opus 4.5
Design Arena: agents building Android apps1176Not measuredOnly Claude Opus 4.5 measured
τ²-Bench Telecom89.5%Not measuredOnly Claude Opus 4.5 measured
METR time horizons75.0%67.4%Claude Opus 4.5
Remote Labor Index3.8%2.1%Claude Opus 4.5
GDPval45.5%42.5%Claude Opus 4.5
BALROG43.5%Not measuredOnly Claude Opus 4.5 measured
DeepResearch Bench54.8%52.6%Claude Opus 4.5
OSWorld66.3%62.9%Claude Opus 4.5
Vending-Bench 2$4,967$3,839Claude Opus 4.5
Berkeley Function Calling Leaderboard (BFCL)77.5%73.2%Claude Opus 4.5
Neither model has a result on the other 27 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index140
Reasoning benchmarks for Claude Opus 4.5 and Claude Sonnet 4.5
BenchmarkClaude Opus 4.5Claude Sonnet 4.5Leader
GPQA Diamond85.9%81.6%Claude Opus 4.5
MMMU Pro (Vals AI)83.0%79.3%Claude Opus 4.5
GPQA Diamond (Artificial Analysis run)86.6%Not measuredOnly Claude Opus 4.5 measured
Humanity's Last Exam (Artificial Analysis run)30.1%Not measuredOnly Claude Opus 4.5 measured
GPQA Diamond (Epoch AI run)86.0%82.3%Claude Opus 4.5
ARC-AGI80.0%63.7%Claude Opus 4.5
ARC-AGI-237.6%13.6%Claude Opus 4.5
SimpleBench62.0%54.3%Claude Opus 4.5
Chess puzzles14.0%10.0%Claude Opus 4.5
Mystery game puzzles22.0%17.0%Claude Opus 4.5
EBR-bench14.3%2.4%Claude Opus 4.5
VPCT40.0%39.8%Claude Opus 4.5
LMArena Text: hard prompts14761462Claude Opus 4.5
LMArena Text: expert14871483Claude Opus 4.5
LMArena Text: hard prompts in English14821471Claude Opus 4.5
Kagi LLM Benchmark80.2%57.9%Claude Opus 4.5
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index80
Math benchmarks for Claude Opus 4.5 and Claude Sonnet 4.5
BenchmarkClaude Opus 4.5Claude Sonnet 4.5Leader
AIME95.4%88.2%Claude Opus 4.5
MGSM (Vals AI)95.2%94.3%Claude Opus 4.5
AA Math Index91.3Not measuredOnly Claude Opus 4.5 measured
AIME 2025 (Artificial Analysis run)91.3%Not measuredOnly Claude Opus 4.5 measured
OTIS Mock AIME86.1%77.8%Claude Opus 4.5
FrontierMath, tiers 1 to 334.4%23.9%Claude Opus 4.5
FrontierMath, tier 44.9%2.4%Claude Opus 4.5
ProofBench36.0%19.0%Claude Opus 4.5
MATH level 5Not measured97.7%Only Claude Sonnet 4.5 measured
LMArena Text: math14631449Claude Opus 4.5
LMArena Text: mathematical work14681462Claude Opus 4.5
Neither model has a result on the other 2 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index122
Knowledge benchmarks for Claude Opus 4.5 and Claude Sonnet 4.5
BenchmarkClaude Opus 4.5Claude Sonnet 4.5Leader
MMLU Pro87.3%87.4%Claude Sonnet 4.5
LegalBench (Vals AI)84.6%84.1%Claude Opus 4.5
CaseLaw (Vals AI)62.6%62.2%Claude Opus 4.5
CorpFin (Vals AI)65.1%62.0%Claude Opus 4.5
TaxEval (Vals AI)74.9%73.3%Claude Opus 4.5
MortgageTax (Vals AI)68.7%64.0%Claude Opus 4.5
MedQA (Vals AI)95.9%94.7%Claude Opus 4.5
MedCode (Vals AI)49.2%44.1%Claude Opus 4.5
MMLU Pro (Artificial Analysis run)89.5%Not measuredOnly Claude Opus 4.5 measured
SimpleQA Verified45.7%30.7%Claude Opus 4.5
GeoBench75.0%Not measuredOnly Claude Opus 4.5 measured
LMArena Text: science14541448Claude Opus 4.5
LMArena Text: medicine and healthcare14441444Claude Sonnet 4.5
LMArena Text: legal and government14591451Claude Opus 4.5
LMArena Text: business and finance14481440Claude Opus 4.5
FACTS Benchmark Suite43.9%40.6%Claude Opus 4.5
Neither model has a result on the other 2 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index71
Web design benchmarks for Claude Opus 4.5 and Claude Sonnet 4.5
BenchmarkClaude Opus 4.5Claude Sonnet 4.5Leader
Design Arena: websites12471189Claude Opus 4.5
Design Arena: UI components12351170Claude Opus 4.5
Design Arena: game dev12281166Claude Opus 4.5
Design Arena: data viz12431167Claude Opus 4.5
Design Arena: 3D12131157Claude Opus 4.5
Design Arena: all code categories12421182Claude Opus 4.5
Design Arena: SVG11801115Claude Opus 4.5
Design Arena: ASCII art11901205Claude 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 index211
General benchmarks for Claude Opus 4.5 and Claude Sonnet 4.5
BenchmarkClaude Opus 4.5Claude Sonnet 4.5Leader
SAGE (Vals AI)52.1%36.1%Claude Opus 4.5
MedScribe (Vals AI)85.3%84.5%Claude Opus 4.5
IFBench58.0%Not measuredOnly Claude Opus 4.5 measured
Long context reasoning (AA-LCR)77.3%Not measuredOnly Claude Opus 4.5 measured
DTBench89.9%83.2%Claude Opus 4.5
LMCA44.5%38.8%Claude Opus 4.5
CL-bench21.1%Not measuredOnly Claude Opus 4.5 measured
Furniture assembly28.3%Not measuredOnly Claude Opus 4.5 measured
LMArena Text14511438Claude Opus 4.5
LMArena Text: instruction following14781459Claude Opus 4.5
LMArena Text: creative writing14451442Claude Opus 4.5
LMArena Text: English14611450Claude Opus 4.5
LMArena Text: non-English14381425Claude Opus 4.5
LMArena Text: Chinese14701460Claude Opus 4.5
LMArena Text: German14491427Claude Opus 4.5
LMArena Text: Japanese14171390Claude Opus 4.5
LMArena Text: Korean14241402Claude Opus 4.5
LMArena Text: French14711459Claude Opus 4.5
LMArena Text: Spanish14571458Claude Sonnet 4.5
LMArena Text: Russian14471437Claude Opus 4.5
LMArena Text: Polish14391423Claude Opus 4.5
LMArena Text: multi-turn14661465Claude Opus 4.5
LMArena Text: longer queries14791475Claude Opus 4.5
LMArena Text: writing and language14521442Claude Opus 4.5
LMArena Text: entertainment and media14341428Claude Opus 4.5
LMArena Document14621450Claude Opus 4.5
Neither model has a result on the other 20 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Opus 4.5 and Claude Sonnet 4.5
BenchmarkClaude Opus 4.5Claude 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 4.5$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 4.5$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 4.5$1.25Exceeds 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 4.5 and Claude Sonnet 4.5
SpecificationAnthropic Claude Opus 4.5Anthropic Claude Sonnet 4.5
MakerAnthropicAnthropic
WeightsNo public weights listedNo public weights listed
ReleasedNovember 24, 2025September 29, 2025
Context window200K1M
Input $/Mtok$5.00$3.00
Output $/Mtok$25.00$15.00
Coding index44.039.5
Independent measurements behind it33
Cost per solved task$1.37$1.16
SourceOpenRouter listingOpenRouter listing

Questions

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

Pick Claude Opus 4.5 for coding: it scores 44.0 on the Vibe Coding Index against 39.5 for Claude Sonnet 4.5. Pick Claude Sonnet 4.5 for output tokens 1.7x cheaper ($15.00 vs $25.00 per million) and a lower cost per solved task ($1.16 against $1.37).

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

Claude Opus 4.5 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 4.5 costs $1.37 and Claude Sonnet 4.5 $1.16.

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

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

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

92 benchmarks have a result for both models as of October 22, 2026. Claude Opus 4.5's coding index rests on 3 independent benchmarks and Claude Sonnet 4.5's on 3. 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-4-5-vs-claude-sonnet-4-5" title="Claude Opus 4.5 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-4-5-vs-claude-sonnet-4-5">LLMBenchmark.ai, Claude Opus 4.5 vs Claude Sonnet 4.5</a></p>