Enter opens the highlighted result. Esc closes.

Claude Opus 4.7 vs Claude Opus 4.8

Claude Opus 4.7 leads Claude Opus 4.8 on coding, 67.5 to 65.0 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 4.7 Replace Claude Opus 4.8
Claude Opus 4.7Anthropic
Coding
67.5
Overall
71.6
Output $/M
$25.00
51
Claude Opus 4.8Anthropic
Coding
65.0
Overall
69.8
Output $/M
$25.00
45
vs boards won of 96 shared

Claude Opus 4.7 or Claude Opus 4.8: which to pick

Pick Claude Opus 4.7 for coding: it scores 67.5 on the Vibe Coding Index against 65.0 for Claude Opus 4.8, though on 4 benchmarks against 6.

Pick Claude Opus 4.8 for a lower cost per solved task ($2.17 against $2.95) and work measured by AA Coding Index or LiveCodeBench (Vals AI), where it leads.

Model AClaude Opus 4.7Anthropic67.5/1004 independent benchmarks$2.95 per solved taskModel BClaude Opus 4.8Anthropic65.0/1006 independent benchmarks$2.17 per solved task
Shared results
96
Claude Opus 4.7 only
7
Claude Opus 4.8 only
34
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 4.7 67.5 from 4 benchmarks, Claude Opus 4.8 65.0 from 6 benchmarks.
Widest category
Math, 9.0 points apart on average over 6 shared benchmarks.
Widest single gap
Vending-Bench 2: Claude Opus 4.7 $10,937 against Claude Opus 4.8 $5,787, 32.2 points apart on a 0 to 100 scale.
Output price
Both cost $25.00 per million output tokens.
Context window
Both take 1M tokens.

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 4.7BarsClaude Opus 4.8Ties
Coding511
Intelligence02
Agentic work38
Reasoning710
Math24
Knowledge84
General266
All shared boards5145
CodingLike-for-likeSix of these boards feed the Vibe Coding Index511
Coding benchmarks for Claude Opus 4.7 and Claude Opus 4.8
BenchmarkClaude Opus 4.7Claude Opus 4.8Leader
LiveBench codingNot measured77.3%Only Claude Opus 4.8 measured
LMArena WebDev15581556Claude Opus 4.7
AA Coding Index73.674.3Claude Opus 4.8
LiveCodeBench (Vals AI)85.1%87.8%Claude Opus 4.8
SWE-bench Verified (Vals AI)82.0%88.6%Claude Opus 4.8
Terminal-Bench 4 (Vals AI)Not measured23.2%Only Claude Opus 4.8 measured
Vibe Code Bench (Vals AI)71.0%82.7%Claude Opus 4.8
Code migration (Vals AI)43.9%47.3%Claude Opus 4.8
ProgramBench (Vals AI)0.0%1.0%Claude Opus 4.8
Terminal-Bench 2.1 (Vals AI)68.5%71.9%Claude Opus 4.8
SkillsBench (Vals AI)Not measured59.2%Only Claude Opus 4.8 measured
SciCodeNot measured54.4%Only Claude Opus 4.8 measured
Terminal-Bench Hard (Artificial Analysis run)54.5%58.3%Claude Opus 4.8
Terminal-Bench80.2%Not measuredOnly Claude Opus 4.7 measured
FrontierCode38.5%46.5%Claude Opus 4.8
GSO-Bench44.1%47.1%Claude Opus 4.8
WeirdML76.4%82.9%Claude Opus 4.8
MirrorCode31.1%Not measuredOnly Claude Opus 4.7 measured
LMArena Text: coding15191490Claude Opus 4.7
LMArena Text: software and IT15161488Claude Opus 4.7
LMArena WebDev: React15601557Claude Opus 4.7
LMArena WebDev: HTML15541543Claude Opus 4.7
LMArena WebDev: from an image1577Not measuredOnly Claude Opus 4.7 measured
SciCodeNot measured12.3%Only Claude Opus 4.8 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 4.7 and Claude Opus 4.8
BenchmarkClaude Opus 4.7Claude Opus 4.8Leader
AA Intelligence Index40.741.8Claude Opus 4.8
Epoch Capabilities Index156.8159.0Claude Opus 4.8
Agentic workLike-for-likePublic boards, shown as published, kept out of the index38
Agentic work benchmarks for Claude Opus 4.7 and Claude Opus 4.8
BenchmarkClaude Opus 4.7Claude Opus 4.8Leader
AA Agentic Index38.641.9Claude Opus 4.8
Design Arena: agents building web appsNot measured1233Only Claude Opus 4.8 measured
Design Arena: agents building full-stack appsNot measured1249Only Claude Opus 4.8 measured
Design Arena: agents building mobile appsNot measured1222Only Claude Opus 4.8 measured
Design Arena: agents building Android appsNot measured1233Only Claude Opus 4.8 measured
Design Arena: agents building Godot gamesNot measured1231Only Claude Opus 4.8 measured
Design Arena: agents building gamesNot measured1239Only Claude Opus 4.8 measured
Design Arena: HTML slidesNot measured1171Only Claude Opus 4.8 measured
Design Arena: PowerPoint slidesNot measured1202Only Claude Opus 4.8 measured
Design Arena: spreadsheetsNot measured1303Only Claude Opus 4.8 measured
LiveBench researchNot measured81.8%Only Claude Opus 4.8 measured
LiveBench browserNot measured96.0%Only Claude Opus 4.8 measured
LiveBench long agenticNot measured48.3%Only Claude Opus 4.8 measured
Finance Agent (Vals AI)51.5%53.9%Claude Opus 4.8
Tax Agent Bench (Vals AI)23.7%30.0%Claude Opus 4.8
Legal Research Bench (Vals AI)38.5%43.8%Claude Opus 4.8
Excel Modeling Benchmark (Vals AI)63.7%69.4%Claude Opus 4.8
Terminal-Bench-Science (Vals AI)Not measured4.3%Only Claude Opus 4.8 measured
Time Horizon Index (Vals AI)Not measured11.8%Only Claude Opus 4.8 measured
τ²-Bench Telecom88.6%94.4%Claude Opus 4.8
APEX-Agents49.2%48.9%Claude Opus 4.7
Remote Labor IndexNot measured8.3%Only Claude Opus 4.8 measured
OSWorld 2.018.2%20.6%Claude Opus 4.8
DeepResearch BenchNot measured50.2%Only Claude Opus 4.8 measured
PostTrainBench28.6%33.8%Claude Opus 4.8
Vending-Bench 2$10,937$5,787Claude Opus 4.7
LMArena Search12301204Claude Opus 4.7
Neither model has a result on the other 14 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index710
Reasoning benchmarks for Claude Opus 4.7 and Claude Opus 4.8
BenchmarkClaude Opus 4.7Claude Opus 4.8Leader
GPQA Diamond90.2%92.4%Claude Opus 4.8
LiveBench reasoningNot measured89.2%Only Claude Opus 4.8 measured
MMMU Pro (Vals AI)85.5%86.6%Claude Opus 4.8
GPQA Diamond (Artificial Analysis run)91.4%92.0%Claude Opus 4.8
Humanity's Last Exam (Artificial Analysis run)42.3%48.7%Claude Opus 4.8
GPQA Diamond (Epoch AI run)90.2%91.0%Claude Opus 4.8
ARC-AGI93.5%92.5%Claude Opus 4.7
ARC-AGI-275.8%72.1%Claude Opus 4.7
SimpleBench61.7%64.8%Claude Opus 4.8
Chess puzzles41.0%52.0%Claude Opus 4.8
Mystery game puzzles28.0%36.0%Claude Opus 4.8
EBR-bench19.0%28.6%Claude Opus 4.8
LMArena Text: hard prompts15061482Claude Opus 4.7
LMArena Text: expert15211503Claude Opus 4.7
LMArena Text: hard prompts in English15081487Claude Opus 4.7
LMArena Vision: diagrams13361315Claude Opus 4.7
LMArena Vision: homework13371337Claude Opus 4.7
Kagi LLM Benchmark80.7%88.8%Claude Opus 4.8
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index24
Math benchmarks for Claude Opus 4.7 and Claude Opus 4.8
BenchmarkClaude Opus 4.7Claude Opus 4.8Leader
AIME96.3%Not measuredOnly Claude Opus 4.7 measured
OTIS Mock AIME97.8%98.3%Claude Opus 4.8
FrontierMath, tiers 1 to 370.2%80.0%Claude Opus 4.8
FrontierMath, tier 431.7%56.1%Claude Opus 4.8
ProofBench54.0%69.0%Claude Opus 4.8
LMArena Text: math14981486Claude Opus 4.7
LMArena Text: mathematical work15091497Claude Opus 4.7
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index84
Knowledge benchmarks for Claude Opus 4.7 and Claude Opus 4.8
BenchmarkClaude Opus 4.7Claude Opus 4.8Leader
MMLU Pro89.9%89.6%Claude Opus 4.7
LegalBench (Vals AI)85.3%83.6%Claude Opus 4.7
CaseLaw (Vals AI)68.4%Not measuredOnly Claude Opus 4.7 measured
CorpFin (Vals AI)66.1%66.7%Claude Opus 4.8
TaxEval (Vals AI)75.3%75.6%Claude Opus 4.8
MortgageTax (Vals AI)70.3%69.9%Claude Opus 4.7
MedCode (Vals AI)54.9%53.2%Claude Opus 4.7
SimpleQA Verified51.7%53.0%Claude Opus 4.8
LMArena Text: science15081477Claude Opus 4.7
LMArena Text: medicine and healthcare14951464Claude Opus 4.7
LMArena Text: legal and government15041477Claude Opus 4.7
LMArena Text: business and finance14901458Claude Opus 4.7
FACTS Benchmark Suite45.5%53.5%Claude Opus 4.8
Neither model has a result on the other 5 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Web design benchmarks for Claude Opus 4.7 and Claude Opus 4.8
BenchmarkClaude Opus 4.7Claude Opus 4.8Leader
Design Arena: websitesNot measured1258Only Claude Opus 4.8 measured
Design Arena: UI componentsNot measured1255Only Claude Opus 4.8 measured
Design Arena: game devNot measured1264Only Claude Opus 4.8 measured
Design Arena: data vizNot measured1240Only Claude Opus 4.8 measured
Design Arena: 3DNot measured1222Only Claude Opus 4.8 measured
Design Arena: all code categoriesNot measured1255Only Claude Opus 4.8 measured
Design Arena: SVGNot measured1195Only Claude Opus 4.8 measured
Design Arena: ASCII artNot measured1277Only Claude Opus 4.8 measured
LiveBench designNot measured78.8%Only Claude Opus 4.8 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index266
General benchmarks for Claude Opus 4.7 and Claude Opus 4.8
BenchmarkClaude Opus 4.7Claude Opus 4.8Leader
LiveBench data analysisNot measured66.0%Only Claude Opus 4.8 measured
Public Benefits Bench (Vals AI)Not measured68.1%Only Claude Opus 4.8 measured
SAGE (Vals AI)56.1%54.8%Claude Opus 4.7
MedScribe (Vals AI)83.0%85.8%Claude Opus 4.8
Vals Multimodal Index67.4%70.9%Claude Opus 4.8
IFBench58.6%62.2%Claude Opus 4.8
Long context reasoning (AA-LCR)78.7%77.7%Claude Opus 4.7
DTBench94.7%94.9%Claude Opus 4.8
LMCA52.2%57.5%Claude Opus 4.8
Surface Evolver BenchNot measured87.5%Only Claude Opus 4.8 measured
Furniture assembly33.3%42.5%Claude Opus 4.8
ExploitBench26.5%Not measuredOnly Claude Opus 4.7 measured
LMArena Text14901461Claude Opus 4.7
LMArena Text: instruction following14981476Claude Opus 4.7
LMArena Text: creative writing14861454Claude Opus 4.7
LMArena Vision13171294Claude Opus 4.7
LMArena Text: English14961468Claude Opus 4.7
LMArena Text: non-English14801450Claude Opus 4.7
LMArena Text: Chinese15311506Claude Opus 4.7
LMArena Text: German14951472Claude Opus 4.7
LMArena Text: Japanese14741442Claude Opus 4.7
LMArena Text: Korean14641431Claude Opus 4.7
LMArena Text: French15031481Claude Opus 4.7
LMArena Text: Spanish14941465Claude Opus 4.7
LMArena Text: Russian14941474Claude Opus 4.7
LMArena Text: Polish14891459Claude Opus 4.7
LMArena Text: multi-turn15051476Claude Opus 4.7
LMArena Text: longer queries15051483Claude Opus 4.7
LMArena Text: writing and language14921461Claude Opus 4.7
LMArena Text: entertainment and media14741440Claude Opus 4.7
LMArena Vision: English13221293Claude Opus 4.7
LMArena Vision: Chinese13711346Claude Opus 4.7
LMArena Vision: reading text13271303Claude Opus 4.7
LMArena Vision: humor13091282Claude Opus 4.7
LMArena Vision: recognizing things1278Not measuredOnly Claude Opus 4.7 measured
LMArena Vision: creative writing13261301Claude Opus 4.7
LMArena Document14951475Claude Opus 4.7
Neither model has a result on the other 9 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Opus 4.7 and Claude Opus 4.8
BenchmarkClaude Opus 4.7Claude Opus 4.8Leader
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 4.7$0.018Fits in one request
Claude Opus 4.8$0.018Fits in one request

Same cost

Repository review

50K input + 3K output tokens

Claude Opus 4.7$0.325Fits in one request
Claude Opus 4.8$0.325Fits in one request

Same cost

Agent loop

200K input + 10K output tokens

Claude Opus 4.7$1.25Fits in one request
Claude Opus 4.8$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 4.7 and Claude Opus 4.8
SpecificationAnthropic Claude Opus 4.7Anthropic Claude Opus 4.8
MakerAnthropicAnthropic
WeightsNo public weights listedNo public weights listed
ReleasedApril 16, 2026May 27, 2026
Context window1M1M
Input $/Mtok$5.00$5.00
Output $/Mtok$25.00$25.00
Coding index67.565.0
Independent measurements behind it46
Cost per solved task$2.95$2.17
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.7 better than Claude Opus 4.8 for coding?

Pick Claude Opus 4.7 for coding: it scores 67.5 on the Vibe Coding Index against 65.0 for Claude Opus 4.8, though on 4 benchmarks against 6. Pick Claude Opus 4.8 for a lower cost per solved task ($2.17 against $2.95) and work measured by AA Coding Index or LiveCodeBench (Vals AI), where it leads.

Which is cheaper, Claude Opus 4.7 or Claude Opus 4.8?

Claude Opus 4.7 costs $5.00 per million input tokens and $25.00 per million output tokens; Claude Opus 4.8 costs $5.00 and $25.00. Per solved SWE-bench Verified task, Claude Opus 4.7 costs $2.95 and Claude Opus 4.8 $2.17.

Which has the bigger context window, Claude Opus 4.7 or Claude Opus 4.8?

Neither: both take 1M tokens.

How many benchmarks is the Claude Opus 4.7 vs Claude Opus 4.8 comparison based on?

96 benchmarks have a result for both models as of October 22, 2026. Claude Opus 4.7's coding index rests on 4 independent benchmarks and Claude Opus 4.8's on 6. 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-4-7-vs-claude-opus-4-8" title="Claude Opus 4.7 vs Claude Opus 4.8, 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-4-7-vs-claude-opus-4-8">LLMBenchmark.ai, Claude Opus 4.7 vs Claude Opus 4.8</a></p>