Enter opens the highlighted result. Esc closes.

Claude Opus 4.5 vs Claude Opus 4.8

Claude Opus 4.8 leads Claude Opus 4.5 on coding, 65.0 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; 87 benchmarks have a result for both.

Replace Claude Opus 4.5 Replace Claude Opus 4.8
Claude Opus 4.5Anthropic
Coding
44.0
Overall
55.7
Output $/M
$25.00
5
Claude Opus 4.8Anthropic
Coding
65.0
Overall
69.8
Output $/M
$25.00
82
vs boards won of 87 shared

Claude Opus 4.5 or Claude Opus 4.8: which to pick

Pick Claude Opus 4.8 for coding: it scores 65.0 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 $2.17) and work measured by LMArena Text: coding or DeepResearch Bench, where it leads.

Model AClaude Opus 4.5Anthropic44.0/1003 independent benchmarks$1.37 per solved taskModel BClaude Opus 4.8Anthropic65.0/1006 independent benchmarks$2.17 per solved task
Shared results
87
Claude Opus 4.5 only
21
Claude Opus 4.8 only
43
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 4.8 65.0 from 6 benchmarks.
Widest category
Math, 25.1 points apart on average over 6 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): Claude Opus 4.5 20.6% against Claude Opus 4.8 82.7%, 62.1 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 4.8 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 4.8Ties
Coding110
Intelligence02
Agentic work17
Reasoning015
Math06
Knowledge111
Web design17
General124
All shared boards582
CodingLike-for-likeSix of these boards feed the Vibe Coding Index110
Coding benchmarks for Claude Opus 4.5 and Claude Opus 4.8
BenchmarkClaude Opus 4.5Claude Opus 4.8Leader
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
LiveBench codingNot measured77.3%Only Claude Opus 4.8 measured
LMArena WebDev14941556Claude Opus 4.8
AA Coding IndexNot measured74.3Only Claude Opus 4.8 measured
LiveCodeBench (Vals AI)83.7%87.8%Claude Opus 4.8
SWE-bench Verified (Vals AI)76.4%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)20.6%82.7%Claude Opus 4.8
Code migration (Vals AI)Not measured47.3%Only Claude Opus 4.8 measured
ProgramBench (Vals AI)Not measured1.0%Only Claude Opus 4.8 measured
Terminal-Bench 2.1 (Vals AI)Not measured71.9%Only Claude Opus 4.8 measured
SkillsBench (Vals AI)Not measured59.2%Only Claude Opus 4.8 measured
LiveCodeBench (Artificial Analysis run)87.1%Not measuredOnly Claude Opus 4.5 measured
SciCodeNot measured54.4%Only Claude Opus 4.8 measured
Terminal-Bench Hard (Artificial Analysis run)47.0%58.3%Claude Opus 4.8
Terminal-Bench63.1%Not measuredOnly Claude Opus 4.5 measured
FrontierCodeNot measured46.5%Only Claude Opus 4.8 measured
GSO-Bench26.5%47.1%Claude Opus 4.8
WeirdML63.7%82.9%Claude Opus 4.8
Cybench82.0%Not measuredOnly Claude Opus 4.5 measured
LMArena Text: coding15031490Claude Opus 4.5
LMArena Text: software and IT14831488Claude Opus 4.8
LMArena WebDev: React14781557Claude Opus 4.8
LMArena WebDev: HTML15101543Claude Opus 4.8
SciCodeNot measured12.3%Only Claude Opus 4.8 measured
Neither model has a result on the other 12 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Opus 4.5 and Claude Opus 4.8
BenchmarkClaude Opus 4.5Claude Opus 4.8Leader
AA Intelligence Index29.141.8Claude Opus 4.8
Epoch Capabilities Index150.1159.0Claude Opus 4.8
Agentic workLike-for-likePublic boards, shown as published, kept out of the index17
Agentic work benchmarks for Claude Opus 4.5 and Claude Opus 4.8
BenchmarkClaude Opus 4.5Claude Opus 4.8Leader
AA Agentic IndexNot measured41.9Only Claude Opus 4.8 measured
Design Arena: agents building web apps11591233Claude Opus 4.8
Design Arena: agents building full-stack apps11561249Claude Opus 4.8
Design Arena: agents building mobile apps11891222Claude Opus 4.8
Design Arena: agents building Android apps11761233Claude Opus 4.8
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)Not measured53.9%Only Claude Opus 4.8 measured
Tax Agent Bench (Vals AI)Not measured30.0%Only Claude Opus 4.8 measured
Legal Research Bench (Vals AI)Not measured43.8%Only Claude Opus 4.8 measured
Excel Modeling Benchmark (Vals AI)Not measured69.4%Only Claude Opus 4.8 measured
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 Telecom89.5%94.4%Claude Opus 4.8
APEX-AgentsNot measured48.9%Only Claude Opus 4.8 measured
METR time horizons75.0%Not measuredOnly Claude Opus 4.5 measured
Remote Labor Index3.8%8.3%Claude Opus 4.8
GDPval45.5%Not measuredOnly Claude Opus 4.5 measured
OSWorld 2.0Not measured20.6%Only Claude Opus 4.8 measured
BALROG43.5%Not measuredOnly Claude Opus 4.5 measured
DeepResearch Bench54.8%50.2%Claude Opus 4.5
PostTrainBenchNot measured33.8%Only Claude Opus 4.8 measured
OSWorld66.3%Not measuredOnly Claude Opus 4.5 measured
Vending-Bench 2$4,967$5,787Claude Opus 4.8
LMArena SearchNot measured1204Only Claude Opus 4.8 measured
Berkeley Function Calling Leaderboard (BFCL)77.5%Not measuredOnly Claude Opus 4.5 measured
Neither model has a result on the other 9 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index015
Reasoning benchmarks for Claude Opus 4.5 and Claude Opus 4.8
BenchmarkClaude Opus 4.5Claude Opus 4.8Leader
GPQA Diamond85.9%92.4%Claude Opus 4.8
LiveBench reasoningNot measured89.2%Only Claude Opus 4.8 measured
MMMU Pro (Vals AI)83.0%86.6%Claude Opus 4.8
GPQA Diamond (Artificial Analysis run)86.6%92.0%Claude Opus 4.8
Humanity's Last Exam (Artificial Analysis run)30.1%48.7%Claude Opus 4.8
GPQA Diamond (Epoch AI run)86.0%91.0%Claude Opus 4.8
ARC-AGI80.0%92.5%Claude Opus 4.8
ARC-AGI-237.6%72.1%Claude Opus 4.8
SimpleBench62.0%64.8%Claude Opus 4.8
Chess puzzles14.0%52.0%Claude Opus 4.8
Mystery game puzzles22.0%36.0%Claude Opus 4.8
EBR-bench14.3%28.6%Claude Opus 4.8
VPCT40.0%Not measuredOnly Claude Opus 4.5 measured
LMArena Text: hard prompts14761482Claude Opus 4.8
LMArena Text: expert14871503Claude Opus 4.8
LMArena Text: hard prompts in English14821487Claude Opus 4.8
LMArena Vision: diagramsNot measured1315Only Claude Opus 4.8 measured
LMArena Vision: homeworkNot measured1337Only Claude Opus 4.8 measured
Kagi LLM Benchmark80.2%88.8%Claude Opus 4.8
Neither model has a result on the other 3 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index06
Math benchmarks for Claude Opus 4.5 and Claude Opus 4.8
BenchmarkClaude Opus 4.5Claude Opus 4.8Leader
AIME95.4%Not measuredOnly Claude Opus 4.5 measured
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%98.3%Claude Opus 4.8
FrontierMath, tiers 1 to 334.4%80.0%Claude Opus 4.8
FrontierMath, tier 44.9%56.1%Claude Opus 4.8
ProofBench36.0%69.0%Claude Opus 4.8
LMArena Text: math14631486Claude Opus 4.8
LMArena Text: mathematical work14681497Claude Opus 4.8
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index111
Knowledge benchmarks for Claude Opus 4.5 and Claude Opus 4.8
BenchmarkClaude Opus 4.5Claude Opus 4.8Leader
MMLU Pro87.3%89.6%Claude Opus 4.8
LegalBench (Vals AI)84.6%83.6%Claude Opus 4.5
CaseLaw (Vals AI)62.6%Not measuredOnly Claude Opus 4.5 measured
CorpFin (Vals AI)65.1%66.7%Claude Opus 4.8
TaxEval (Vals AI)74.9%75.6%Claude Opus 4.8
MortgageTax (Vals AI)68.7%69.9%Claude Opus 4.8
MedQA (Vals AI)95.9%Not measuredOnly Claude Opus 4.5 measured
MedCode (Vals AI)49.2%53.2%Claude Opus 4.8
MMLU Pro (Artificial Analysis run)89.5%Not measuredOnly Claude Opus 4.5 measured
SimpleQA Verified45.7%53.0%Claude Opus 4.8
GeoBench75.0%Not measuredOnly Claude Opus 4.5 measured
LMArena Text: science14541477Claude Opus 4.8
LMArena Text: medicine and healthcare14441464Claude Opus 4.8
LMArena Text: legal and government14591477Claude Opus 4.8
LMArena Text: business and finance14481458Claude Opus 4.8
FACTS Benchmark Suite43.9%53.5%Claude Opus 4.8
Neither model has a result on the other 2 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index17
Web design benchmarks for Claude Opus 4.5 and Claude Opus 4.8
BenchmarkClaude Opus 4.5Claude Opus 4.8Leader
Design Arena: websites12471258Claude Opus 4.8
Design Arena: UI components12351255Claude Opus 4.8
Design Arena: game dev12281264Claude Opus 4.8
Design Arena: data viz12431240Claude Opus 4.5
Design Arena: 3D12131222Claude Opus 4.8
Design Arena: all code categories12421255Claude Opus 4.8
Design Arena: SVG11801195Claude Opus 4.8
Design Arena: ASCII art11901277Claude Opus 4.8
LiveBench designNot measured78.8%Only Claude Opus 4.8 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index124
General benchmarks for Claude Opus 4.5 and Claude Opus 4.8
BenchmarkClaude Opus 4.5Claude 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)52.1%54.8%Claude Opus 4.8
MedScribe (Vals AI)85.3%85.8%Claude Opus 4.8
Vals Multimodal IndexNot measured70.9%Only Claude Opus 4.8 measured
IFBench58.0%62.2%Claude Opus 4.8
Long context reasoning (AA-LCR)77.3%77.7%Claude Opus 4.8
DTBench89.9%94.9%Claude Opus 4.8
LMCA44.5%57.5%Claude Opus 4.8
CL-bench21.1%Not measuredOnly Claude Opus 4.5 measured
Surface Evolver BenchNot measured87.5%Only Claude Opus 4.8 measured
Furniture assembly28.3%42.5%Claude Opus 4.8
LMArena Text14511461Claude Opus 4.8
LMArena Text: instruction following14781476Claude Opus 4.5
LMArena Text: creative writing14451454Claude Opus 4.8
LMArena VisionNot measured1294Only Claude Opus 4.8 measured
LMArena Text: English14611468Claude Opus 4.8
LMArena Text: non-English14381450Claude Opus 4.8
LMArena Text: Chinese14701506Claude Opus 4.8
LMArena Text: German14491472Claude Opus 4.8
LMArena Text: Japanese14171442Claude Opus 4.8
LMArena Text: Korean14241431Claude Opus 4.8
LMArena Text: French14711481Claude Opus 4.8
LMArena Text: Spanish14571465Claude Opus 4.8
LMArena Text: Russian14471474Claude Opus 4.8
LMArena Text: Polish14391459Claude Opus 4.8
LMArena Text: multi-turn14661476Claude Opus 4.8
LMArena Text: longer queries14791483Claude Opus 4.8
LMArena Text: writing and language14521461Claude Opus 4.8
LMArena Text: entertainment and media14341440Claude Opus 4.8
LMArena Vision: EnglishNot measured1293Only Claude Opus 4.8 measured
LMArena Vision: ChineseNot measured1346Only Claude Opus 4.8 measured
LMArena Vision: reading textNot measured1303Only Claude Opus 4.8 measured
LMArena Vision: humorNot measured1282Only Claude Opus 4.8 measured
LMArena Vision: creative writingNot measured1301Only Claude Opus 4.8 measured
LMArena Document14621475Claude Opus 4.8
Neither model has a result on the other 10 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 4.8
BenchmarkClaude Opus 4.5Claude 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 4.5$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 4.5$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 4.5$1.25Exceeds the context window
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 4.5 and Claude Opus 4.8
SpecificationAnthropic Claude Opus 4.5Anthropic Claude Opus 4.8
MakerAnthropicAnthropic
WeightsNo public weights listedNo public weights listed
ReleasedNovember 24, 2025May 27, 2026
Context window200K1M
Input $/Mtok$5.00$5.00
Output $/Mtok$25.00$25.00
Coding index44.065.0
Independent measurements behind it36
Cost per solved task$1.37$2.17
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.5 better than Claude Opus 4.8 for coding?

Pick Claude Opus 4.8 for coding: it scores 65.0 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 $2.17) and work measured by LMArena Text: coding or DeepResearch Bench, where it leads.

Which is cheaper, Claude Opus 4.5 or Claude Opus 4.8?

Claude Opus 4.5 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 4.5 costs $1.37 and Claude Opus 4.8 $2.17.

Which has the bigger context window, Claude Opus 4.5 or Claude Opus 4.8?

Claude Opus 4.8, with 1M tokens against 200K.

How many benchmarks is the Claude Opus 4.5 vs Claude Opus 4.8 comparison based on?

87 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 4.8'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-4-5-vs-claude-opus-4-8" title="Claude Opus 4.5 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-4-5-vs-claude-opus-4-8">LLMBenchmark.ai, Claude Opus 4.5 vs Claude Opus 4.8</a></p>