Enter opens the highlighted result. Esc closes.

Claude Opus 4.5 vs Claude Opus 4.6

Claude Opus 4.6 leads Claude Opus 4.5 on coding, 57.2 to 44.0 on the Vibe Coding Index, at about the same output price ($25.00 vs $25.00 per million). Updated October 22, 2026; 96 benchmarks have a result for both.

Replace Claude Opus 4.5 Replace Claude Opus 4.6
Claude Opus 4.5Anthropic
Coding
44.0
Overall
55.7
Output $/M
$25.00
10
Claude Opus 4.6Anthropic
Coding
57.2
Overall
66.0
Output $/M
$25.00
85
vs boards won of 96 shared, 1 tied

Claude Opus 4.5 or Claude Opus 4.6: which to pick

Pick Claude Opus 4.6 for coding: it scores 57.2 on the Vibe Coding Index against 44.0 for Claude Opus 4.5.

Pick Claude Opus 4.5 for a lower cost per solved task ($1.37 against $1.56) and work measured by SWE-bench Verified or EBR-bench, where it leads.

Model AClaude Opus 4.5Anthropic44.0/1003 independent benchmarks$1.37 per solved taskModel BClaude Opus 4.6Anthropic57.2/1004 independent benchmarks$1.56 per solved task
Shared results
96
Claude Opus 4.5 only
12
Claude Opus 4.6 only
14
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 Opus 4.6 57.2 from 4 benchmarks.
Widest category
Math, 13.5 points apart on average over 7 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): Claude Opus 4.5 20.6% against Claude Opus 4.6 57.6%, 36.9 points apart on a 0 to 100 scale.
Output price
Both cost $25.00 per million output tokens.
Context window
Claude Opus 4.5 takes 200K tokens, Claude Opus 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 4.5BarsClaude Opus 4.6Ties
Coding114
Intelligence02
Agentic work09
Reasoning114
Math07
Knowledge59
Web design08
General3221 tie
All shared boards10851 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index114
Coding benchmarks for Claude Opus 4.5 and Claude Opus 4.6
BenchmarkClaude Opus 4.5Claude Opus 4.6Leader
SWE-bench Verified79.2%75.6%Claude Opus 4.5
SWE-bench (full test set)52.6%Not measuredOnly Claude Opus 4.5 measured
SWE-bench Multilingual70.7%72.0%Claude Opus 4.6
LMArena WebDev14941547Claude Opus 4.6
LiveCodeBench (Vals AI)83.7%84.7%Claude Opus 4.6
SWE-bench Verified (Vals AI)76.4%78.2%Claude Opus 4.6
Vibe Code Bench (Vals AI)20.6%57.6%Claude Opus 4.6
LiveCodeBench (Artificial Analysis run)87.1%Not measuredOnly Claude Opus 4.5 measured
Terminal-Bench Hard (Artificial Analysis run)47.0%48.5%Claude Opus 4.6
Terminal-Bench63.1%79.8%Claude Opus 4.6
FrontierCodeNot measured26.6%Only Claude Opus 4.6 measured
GSO-Bench26.5%41.2%Claude Opus 4.6
WeirdML63.7%78.0%Claude Opus 4.6
Cybench82.0%93.0%Claude Opus 4.6
LMArena Text: coding15031534Claude Opus 4.6
LMArena Text: software and IT14831527Claude Opus 4.6
LMArena WebDev: React14781539Claude Opus 4.6
LMArena WebDev: HTML15101559Claude Opus 4.6
LMArena WebDev: from an imageNot measured1543Only 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 index02
Intelligence benchmarks for Claude Opus 4.5 and Claude Opus 4.6
BenchmarkClaude Opus 4.5Claude Opus 4.6Leader
AA Intelligence Index29.131.9Claude Opus 4.6
Epoch Capabilities Index150.1155.7Claude Opus 4.6
Agentic workLike-for-likePublic boards, shown as published, kept out of the index09
Agentic work benchmarks for Claude Opus 4.5 and Claude Opus 4.6
BenchmarkClaude Opus 4.5Claude Opus 4.6Leader
Design Arena: agents building web apps11591206Claude Opus 4.6
Design Arena: agents building full-stack apps11561220Claude Opus 4.6
Design Arena: agents building mobile apps11891207Claude Opus 4.6
Design Arena: agents building Android apps11761197Claude Opus 4.6
Design Arena: agents building gamesNot measured1212Only Claude Opus 4.6 measured
τ²-Bench Telecom89.5%92.1%Claude Opus 4.6
APEX-AgentsNot measured46.3%Only Claude Opus 4.6 measured
METR time horizons75.0%78.9%Claude Opus 4.6
Remote Labor Index3.8%4.2%Claude Opus 4.6
GDPval45.5%Not measuredOnly Claude Opus 4.5 measured
BALROG43.5%Not measuredOnly Claude Opus 4.5 measured
DeepResearch Bench54.8%55.3%Claude Opus 4.6
OSWorld66.3%Not measuredOnly Claude Opus 4.5 measured
Vending-Bench 2$4,967$8,018Claude Opus 4.6
Berkeley Function Calling Leaderboard (BFCL)77.5%Not measuredOnly Claude Opus 4.5 measured
Neither model has a result on the other 26 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index114
Reasoning benchmarks for Claude Opus 4.5 and Claude Opus 4.6
BenchmarkClaude Opus 4.5Claude Opus 4.6Leader
GPQA Diamond85.9%89.7%Claude Opus 4.6
MMMU Pro (Vals AI)83.0%83.9%Claude Opus 4.6
GPQA Diamond (Artificial Analysis run)86.6%89.6%Claude Opus 4.6
Humanity's Last Exam (Artificial Analysis run)30.1%39.9%Claude Opus 4.6
GPQA Diamond (Epoch AI run)86.0%90.5%Claude Opus 4.6
ARC-AGI80.0%94.0%Claude Opus 4.6
ARC-AGI-237.6%69.2%Claude Opus 4.6
SimpleBench62.0%67.6%Claude Opus 4.6
Chess puzzles14.0%21.0%Claude Opus 4.6
Mystery game puzzles22.0%25.0%Claude Opus 4.6
EBR-bench14.3%12.7%Claude Opus 4.5
VPCT40.0%Not measuredOnly Claude Opus 4.5 measured
LMArena Text: hard prompts14761525Claude Opus 4.6
LMArena Text: expert14871544Claude Opus 4.6
LMArena Text: hard prompts in English14821530Claude Opus 4.6
LMArena Vision: diagramsNot measured1340Only Claude Opus 4.6 measured
LMArena Vision: homeworkNot measured1337Only Claude Opus 4.6 measured
Kagi LLM Benchmark80.2%83.6%Claude Opus 4.6
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index07
Math benchmarks for Claude Opus 4.5 and Claude Opus 4.6
BenchmarkClaude Opus 4.5Claude Opus 4.6Leader
AIME95.4%95.6%Claude Opus 4.6
MGSM (Vals AI)95.2%Not measuredOnly Claude Opus 4.5 measured
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%94.4%Claude Opus 4.6
FrontierMath, tiers 1 to 334.4%66.0%Claude Opus 4.6
FrontierMath, tier 44.9%26.8%Claude Opus 4.6
ProofBench36.0%50.0%Claude Opus 4.6
LMArena Text: math14631518Claude Opus 4.6
LMArena Text: mathematical work14681525Claude Opus 4.6
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index59
Knowledge benchmarks for Claude Opus 4.5 and Claude Opus 4.6
BenchmarkClaude Opus 4.5Claude Opus 4.6Leader
MMLU Pro87.3%89.1%Claude Opus 4.6
LegalBench (Vals AI)84.6%85.3%Claude Opus 4.6
CaseLaw (Vals AI)62.6%62.1%Claude Opus 4.5
CorpFin (Vals AI)65.1%67.0%Claude Opus 4.6
TaxEval (Vals AI)74.9%76.0%Claude Opus 4.6
MortgageTax (Vals AI)68.7%68.5%Claude Opus 4.5
MedQA (Vals AI)95.9%95.4%Claude Opus 4.5
MedCode (Vals AI)49.2%49.1%Claude Opus 4.5
MMLU Pro (Artificial Analysis run)89.5%Not measuredOnly Claude Opus 4.5 measured
SimpleQA Verified45.7%47.0%Claude Opus 4.6
GeoBench75.0%Not measuredOnly Claude Opus 4.5 measured
LMArena Text: science14541519Claude Opus 4.6
LMArena Text: medicine and healthcare14441504Claude Opus 4.6
LMArena Text: legal and government14591512Claude Opus 4.6
LMArena Text: business and finance14481497Claude Opus 4.6
FACTS Benchmark Suite43.9%41.5%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 index08
Web design benchmarks for Claude Opus 4.5 and Claude Opus 4.6
BenchmarkClaude Opus 4.5Claude Opus 4.6Leader
Design Arena: websites12471291Claude Opus 4.6
Design Arena: UI components12351281Claude Opus 4.6
Design Arena: game dev12281277Claude Opus 4.6
Design Arena: data viz12431279Claude Opus 4.6
Design Arena: 3D12131273Claude Opus 4.6
Design Arena: all code categories12421288Claude Opus 4.6
Design Arena: SVG11801227Claude Opus 4.6
Design Arena: ASCII art11901255Claude 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 index322
General benchmarks for Claude Opus 4.5 and Claude Opus 4.6
BenchmarkClaude Opus 4.5Claude Opus 4.6Leader
SAGE (Vals AI)52.1%51.6%Claude Opus 4.5
MedScribe (Vals AI)85.3%86.7%Claude Opus 4.6
IFBench58.0%53.1%Claude Opus 4.5
Long context reasoning (AA-LCR)77.3%78.0%Claude Opus 4.6
DTBench89.9%91.2%Claude Opus 4.6
LMCA44.5%55.8%Claude Opus 4.6
CL-bench21.1%20.7%Claude Opus 4.5
Furniture assembly28.3%28.3%Tie
CL-bench LifeNot measured17.0%Only Claude Opus 4.6 measured
LMArena Text14511501Claude Opus 4.6
LMArena Text: instruction following14781521Claude Opus 4.6
LMArena Text: creative writing14451505Claude Opus 4.6
LMArena VisionNot measured1316Only Claude Opus 4.6 measured
LMArena Text: English14611511Claude Opus 4.6
LMArena Text: non-English14381488Claude Opus 4.6
LMArena Text: Chinese14701551Claude Opus 4.6
LMArena Text: German14491500Claude Opus 4.6
LMArena Text: Japanese14171488Claude Opus 4.6
LMArena Text: Korean14241464Claude Opus 4.6
LMArena Text: French14711512Claude Opus 4.6
LMArena Text: Spanish14571510Claude Opus 4.6
LMArena Text: Russian14471497Claude Opus 4.6
LMArena Text: Polish14391499Claude Opus 4.6
LMArena Text: multi-turn14661511Claude Opus 4.6
LMArena Text: longer queries14791518Claude Opus 4.6
LMArena Text: writing and language14521502Claude Opus 4.6
LMArena Text: entertainment and media14341492Claude Opus 4.6
LMArena Vision: EnglishNot measured1324Only Claude Opus 4.6 measured
LMArena Vision: ChineseNot measured1370Only Claude Opus 4.6 measured
LMArena Vision: reading textNot measured1326Only Claude Opus 4.6 measured
LMArena Vision: humorNot measured1314Only Claude Opus 4.6 measured
LMArena Vision: recognizing thingsNot measured1274Only Claude Opus 4.6 measured
LMArena Vision: creative writingNot measured1331Only Claude Opus 4.6 measured
LMArena Document14621507Claude 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 4.5 and Claude Opus 4.6
BenchmarkClaude Opus 4.5Claude Opus 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 4.5$0.018Fits in one request
Claude Opus 4.6$0.018Fits in one request

Same cost

Repository review

50K input + 3K output tokens

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

Same cost

Agent loop

200K input + 10K output tokens

Claude Opus 4.5$1.25Exceeds the context window
Claude Opus 4.6$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 4.5 and Claude Opus 4.6
SpecificationAnthropic Claude Opus 4.5Anthropic Claude Opus 4.6
MakerAnthropicAnthropic
WeightsNo public weights listedNo public weights listed
ReleasedNovember 24, 2025February 4, 2026
Context window200K1M
Input $/Mtok$5.00$5.00
Output $/Mtok$25.00$25.00
Coding index44.057.2
Independent measurements behind it34
Cost per solved task$1.37$1.56
SourceOpenRouter listingOpenRouter listing

Questions

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

Pick Claude Opus 4.6 for coding: it scores 57.2 on the Vibe Coding Index against 44.0 for Claude Opus 4.5. Pick Claude Opus 4.5 for a lower cost per solved task ($1.37 against $1.56) and work measured by SWE-bench Verified or EBR-bench, where it leads.

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

Claude Opus 4.5 costs $5.00 per million input tokens and $25.00 per million output tokens; Claude Opus 4.6 costs $5.00 and $25.00. Per solved SWE-bench Verified task, Claude Opus 4.5 costs $1.37 and Claude Opus 4.6 $1.56.

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

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

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

96 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 Opus 4.6's on 4. 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-opus-4-6" title="Claude Opus 4.5 vs Claude Opus 4.6, 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-opus-4-6">LLMBenchmark.ai, Claude Opus 4.5 vs Claude Opus 4.6</a></p>