Enter opens the highlighted result. Esc closes.

Claude Opus 4.5 vs Claude Opus 4.7

Claude Opus 4.7 leads Claude Opus 4.5 on coding, 67.5 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; 76 benchmarks have a result for both.

Replace Claude Opus 4.5 Replace Claude Opus 4.7
Claude Opus 4.5Anthropic
Coding
44.0
Overall
55.7
Output $/M
$25.00
3
Claude Opus 4.7Anthropic
Coding
67.5
Overall
71.6
Output $/M
$25.00
73
vs boards won of 76 shared

Claude Opus 4.5 or Claude Opus 4.7: which to pick

Pick Claude Opus 4.7 for coding: it scores 67.5 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 $2.95) and work measured by τ²-Bench Telecom or SimpleBench, where it leads.

Model AClaude Opus 4.5Anthropic44.0/1003 independent benchmarks$1.37 per solved taskModel BClaude Opus 4.7Anthropic67.5/1004 independent benchmarks$2.95 per solved task
Shared results
76
Claude Opus 4.5 only
32
Claude Opus 4.7 only
27
Like-for-like categories
7 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 4.7 67.5 from 4 benchmarks.
Widest category
Agentic work, 19.1 points apart on average over 2 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): Claude Opus 4.5 20.6% against Claude Opus 4.7 71.0%, 50.4 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 4.7 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 4.7Ties
Coding012
Intelligence02
Agentic work11
Reasoning114
Math07
Knowledge013
General124
All shared boards373
CodingLike-for-likeSix of these boards feed the Vibe Coding Index012
Coding benchmarks for Claude Opus 4.5 and Claude Opus 4.7
BenchmarkClaude Opus 4.5Claude Opus 4.7Leader
SWE-bench Verified79.2%Not measuredOnly Claude Opus 4.5 measured
SWE-bench (full test set)52.6%Not measuredOnly Claude Opus 4.5 measured
SWE-bench Multilingual70.7%Not measuredOnly Claude Opus 4.5 measured
LMArena WebDev14941558Claude Opus 4.7
AA Coding IndexNot measured73.6Only Claude Opus 4.7 measured
LiveCodeBench (Vals AI)83.7%85.1%Claude Opus 4.7
SWE-bench Verified (Vals AI)76.4%82.0%Claude Opus 4.7
Vibe Code Bench (Vals AI)20.6%71.0%Claude Opus 4.7
Code migration (Vals AI)Not measured43.9%Only Claude Opus 4.7 measured
ProgramBench (Vals AI)Not measured0.0%Only Claude Opus 4.7 measured
Terminal-Bench 2.1 (Vals AI)Not measured68.5%Only Claude Opus 4.7 measured
LiveCodeBench (Artificial Analysis run)87.1%Not measuredOnly Claude Opus 4.5 measured
Terminal-Bench Hard (Artificial Analysis run)47.0%54.5%Claude Opus 4.7
Terminal-Bench63.1%80.2%Claude Opus 4.7
FrontierCodeNot measured38.5%Only Claude Opus 4.7 measured
GSO-Bench26.5%44.1%Claude Opus 4.7
WeirdML63.7%76.4%Claude Opus 4.7
MirrorCodeNot measured31.1%Only Claude Opus 4.7 measured
Cybench82.0%Not measuredOnly Claude Opus 4.5 measured
LMArena Text: coding15031519Claude Opus 4.7
LMArena Text: software and IT14831516Claude Opus 4.7
LMArena WebDev: React14781560Claude Opus 4.7
LMArena WebDev: HTML15101554Claude Opus 4.7
LMArena WebDev: from an imageNot measured1577Only Claude Opus 4.7 measured
Neither model has a result on the other 15 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Opus 4.5 and Claude Opus 4.7
BenchmarkClaude Opus 4.5Claude Opus 4.7Leader
AA Intelligence Index29.140.7Claude Opus 4.7
Epoch Capabilities Index150.1156.8Claude Opus 4.7
Agentic workLike-for-likePublic boards, shown as published, kept out of the index11
Agentic work benchmarks for Claude Opus 4.5 and Claude Opus 4.7
BenchmarkClaude Opus 4.5Claude Opus 4.7Leader
AA Agentic IndexNot measured38.6Only Claude Opus 4.7 measured
Design Arena: agents building web apps1159Not measuredOnly Claude Opus 4.5 measured
Design Arena: agents building full-stack apps1156Not measuredOnly Claude Opus 4.5 measured
Design Arena: agents building mobile apps1189Not measuredOnly Claude Opus 4.5 measured
Design Arena: agents building Android apps1176Not measuredOnly Claude Opus 4.5 measured
Finance Agent (Vals AI)Not measured51.5%Only Claude Opus 4.7 measured
Tax Agent Bench (Vals AI)Not measured23.7%Only Claude Opus 4.7 measured
Legal Research Bench (Vals AI)Not measured38.5%Only Claude Opus 4.7 measured
Excel Modeling Benchmark (Vals AI)Not measured63.7%Only Claude Opus 4.7 measured
τ²-Bench Telecom89.5%88.6%Claude Opus 4.5
APEX-AgentsNot measured49.2%Only Claude Opus 4.7 measured
METR time horizons75.0%Not measuredOnly Claude Opus 4.5 measured
Remote Labor Index3.8%Not measuredOnly Claude Opus 4.5 measured
GDPval45.5%Not measuredOnly Claude Opus 4.5 measured
OSWorld 2.0Not measured18.2%Only Claude Opus 4.7 measured
BALROG43.5%Not measuredOnly Claude Opus 4.5 measured
DeepResearch Bench54.8%Not measuredOnly Claude Opus 4.5 measured
PostTrainBenchNot measured28.6%Only Claude Opus 4.7 measured
OSWorld66.3%Not measuredOnly Claude Opus 4.5 measured
Vending-Bench 2$4,967$10,937Claude Opus 4.7
LMArena SearchNot measured1230Only Claude Opus 4.7 measured
Berkeley Function Calling Leaderboard (BFCL)77.5%Not measuredOnly Claude Opus 4.5 measured
Neither model has a result on the other 19 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index114
Reasoning benchmarks for Claude Opus 4.5 and Claude Opus 4.7
BenchmarkClaude Opus 4.5Claude Opus 4.7Leader
GPQA Diamond85.9%90.2%Claude Opus 4.7
MMMU Pro (Vals AI)83.0%85.5%Claude Opus 4.7
GPQA Diamond (Artificial Analysis run)86.6%91.4%Claude Opus 4.7
Humanity's Last Exam (Artificial Analysis run)30.1%42.3%Claude Opus 4.7
GPQA Diamond (Epoch AI run)86.0%90.2%Claude Opus 4.7
ARC-AGI80.0%93.5%Claude Opus 4.7
ARC-AGI-237.6%75.8%Claude Opus 4.7
SimpleBench62.0%61.7%Claude Opus 4.5
Chess puzzles14.0%41.0%Claude Opus 4.7
Mystery game puzzles22.0%28.0%Claude Opus 4.7
EBR-bench14.3%19.0%Claude Opus 4.7
VPCT40.0%Not measuredOnly Claude Opus 4.5 measured
LMArena Text: hard prompts14761506Claude Opus 4.7
LMArena Text: expert14871521Claude Opus 4.7
LMArena Text: hard prompts in English14821508Claude Opus 4.7
LMArena Vision: diagramsNot measured1336Only Claude Opus 4.7 measured
LMArena Vision: homeworkNot measured1337Only Claude Opus 4.7 measured
Kagi LLM Benchmark80.2%80.7%Claude Opus 4.7
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 4.7
BenchmarkClaude Opus 4.5Claude Opus 4.7Leader
AIME95.4%96.3%Claude Opus 4.7
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%97.8%Claude Opus 4.7
FrontierMath, tiers 1 to 334.4%70.2%Claude Opus 4.7
FrontierMath, tier 44.9%31.7%Claude Opus 4.7
ProofBench36.0%54.0%Claude Opus 4.7
LMArena Text: math14631498Claude Opus 4.7
LMArena Text: mathematical work14681509Claude Opus 4.7
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index013
Knowledge benchmarks for Claude Opus 4.5 and Claude Opus 4.7
BenchmarkClaude Opus 4.5Claude Opus 4.7Leader
MMLU Pro87.3%89.9%Claude Opus 4.7
LegalBench (Vals AI)84.6%85.3%Claude Opus 4.7
CaseLaw (Vals AI)62.6%68.4%Claude Opus 4.7
CorpFin (Vals AI)65.1%66.1%Claude Opus 4.7
TaxEval (Vals AI)74.9%75.3%Claude Opus 4.7
MortgageTax (Vals AI)68.7%70.3%Claude Opus 4.7
MedQA (Vals AI)95.9%Not measuredOnly Claude Opus 4.5 measured
MedCode (Vals AI)49.2%54.9%Claude Opus 4.7
MMLU Pro (Artificial Analysis run)89.5%Not measuredOnly Claude Opus 4.5 measured
SimpleQA Verified45.7%51.7%Claude Opus 4.7
GeoBench75.0%Not measuredOnly Claude Opus 4.5 measured
LMArena Text: science14541508Claude Opus 4.7
LMArena Text: medicine and healthcare14441495Claude Opus 4.7
LMArena Text: legal and government14591504Claude Opus 4.7
LMArena Text: business and finance14481490Claude Opus 4.7
FACTS Benchmark Suite43.9%45.5%Claude Opus 4.7
Neither model has a result on the other 2 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for Claude Opus 4.5 and Claude Opus 4.7
BenchmarkClaude Opus 4.5Claude Opus 4.7Leader
Design Arena: websites1247Not measuredOnly Claude Opus 4.5 measured
Design Arena: UI components1235Not measuredOnly Claude Opus 4.5 measured
Design Arena: game dev1228Not measuredOnly Claude Opus 4.5 measured
Design Arena: data viz1243Not measuredOnly Claude Opus 4.5 measured
Design Arena: 3D1213Not measuredOnly Claude Opus 4.5 measured
Design Arena: all code categories1242Not measuredOnly Claude Opus 4.5 measured
Design Arena: SVG1180Not measuredOnly Claude Opus 4.5 measured
Design Arena: ASCII art1190Not measuredOnly Claude Opus 4.5 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index124
General benchmarks for Claude Opus 4.5 and Claude Opus 4.7
BenchmarkClaude Opus 4.5Claude Opus 4.7Leader
SAGE (Vals AI)52.1%56.1%Claude Opus 4.7
MedScribe (Vals AI)85.3%83.0%Claude Opus 4.5
Vals Multimodal IndexNot measured67.4%Only Claude Opus 4.7 measured
IFBench58.0%58.6%Claude Opus 4.7
Long context reasoning (AA-LCR)77.3%78.7%Claude Opus 4.7
DTBench89.9%94.7%Claude Opus 4.7
LMCA44.5%52.2%Claude Opus 4.7
CL-bench21.1%Not measuredOnly Claude Opus 4.5 measured
Furniture assembly28.3%33.3%Claude Opus 4.7
ExploitBenchNot measured26.5%Only Claude Opus 4.7 measured
LMArena Text14511490Claude Opus 4.7
LMArena Text: instruction following14781498Claude Opus 4.7
LMArena Text: creative writing14451486Claude Opus 4.7
LMArena VisionNot measured1317Only Claude Opus 4.7 measured
LMArena Text: English14611496Claude Opus 4.7
LMArena Text: non-English14381480Claude Opus 4.7
LMArena Text: Chinese14701531Claude Opus 4.7
LMArena Text: German14491495Claude Opus 4.7
LMArena Text: Japanese14171474Claude Opus 4.7
LMArena Text: Korean14241464Claude Opus 4.7
LMArena Text: French14711503Claude Opus 4.7
LMArena Text: Spanish14571494Claude Opus 4.7
LMArena Text: Russian14471494Claude Opus 4.7
LMArena Text: Polish14391489Claude Opus 4.7
LMArena Text: multi-turn14661505Claude Opus 4.7
LMArena Text: longer queries14791505Claude Opus 4.7
LMArena Text: writing and language14521492Claude Opus 4.7
LMArena Text: entertainment and media14341474Claude Opus 4.7
LMArena Vision: EnglishNot measured1322Only Claude Opus 4.7 measured
LMArena Vision: ChineseNot measured1371Only Claude Opus 4.7 measured
LMArena Vision: reading textNot measured1327Only Claude Opus 4.7 measured
LMArena Vision: humorNot measured1309Only Claude Opus 4.7 measured
LMArena Vision: recognizing thingsNot measured1278Only Claude Opus 4.7 measured
LMArena Vision: creative writingNot measured1326Only Claude Opus 4.7 measured
LMArena Document14621495Claude Opus 4.7
Neither model has a result on the other 11 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 4.7
BenchmarkClaude Opus 4.5Claude Opus 4.7Leader
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 4.7$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 4.7$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 4.7$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 4.7
SpecificationAnthropic Claude Opus 4.5Anthropic Claude Opus 4.7
MakerAnthropicAnthropic
WeightsNo public weights listedNo public weights listed
ReleasedNovember 24, 2025April 16, 2026
Context window200K1M
Input $/Mtok$5.00$5.00
Output $/Mtok$25.00$25.00
Coding index44.067.5
Independent measurements behind it34
Cost per solved task$1.37$2.95
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.5 better than Claude Opus 4.7 for coding?

Pick Claude Opus 4.7 for coding: it scores 67.5 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 $2.95) and work measured by τ²-Bench Telecom or SimpleBench, where it leads.

Which is cheaper, Claude Opus 4.5 or Claude Opus 4.7?

Claude Opus 4.5 costs $5.00 per million input tokens and $25.00 per million output tokens; Claude Opus 4.7 costs $5.00 and $25.00. Per solved SWE-bench Verified task, Claude Opus 4.5 costs $1.37 and Claude Opus 4.7 $2.95.

Which has the bigger context window, Claude Opus 4.5 or Claude Opus 4.7?

Claude Opus 4.7, with 1M tokens against 200K.

How many benchmarks is the Claude Opus 4.5 vs Claude Opus 4.7 comparison based on?

76 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 4.7'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-4-7" title="Claude Opus 4.5 vs Claude Opus 4.7, 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-4-7">LLMBenchmark.ai, Claude Opus 4.5 vs Claude Opus 4.7</a></p>