Enter opens the highlighted result. Esc closes.

Claude Opus 4.8 vs Claude Opus 5.5

Claude Opus 5.5 leads Claude Opus 4.8 on coding, 88.8 to 65.0 on the Vibe Coding Index, and Claude Opus 5.5 costs 1.3x less per output token ($20.00 vs $25.00 per million). Updated October 22, 2026; 92 benchmarks have a result for both.

Replace Claude Opus 4.8 Replace Claude Opus 5.5
Claude Opus 4.8Anthropic
Coding
65.0
Overall
69.8
Output $/M
$25.00
4
Claude Opus 5.5Anthropic
Coding
88.8
Overall
87.1
Output $/M
$20.00
88
vs boards won of 92 shared

Claude Opus 4.8 or Claude Opus 5.5: which to pick

Pick Claude Opus 5.5 for coding: it scores 88.8 on the Vibe Coding Index against 65.0 for Claude Opus 4.8, though on 5 benchmarks against 6.

Pick Claude Opus 4.8 for work measured by LiveBench browser or GPQA Diamond (Epoch AI run), where it leads.

Model AClaude Opus 4.8Anthropic65.0/1006 independent benchmarks$2.17 per solved taskModel BClaude Opus 5.5Anthropic88.8/1005 independent benchmarksNo cost per solved task
Shared results
92
Claude Opus 4.8 only
38
Claude Opus 5.5 only
17
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 4.8 65.0 from 6 benchmarks, Claude Opus 5.5 88.8 from 5 benchmarks.
Widest category
Agentic work, 18.9 points apart on average over 16 shared benchmarks.
Widest single gap
Time Horizon Index (Vals AI): Claude Opus 4.8 11.8% against Claude Opus 5.5 91.3%, 79.5 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.8 $25.00 against Claude Opus 5.5 $20.00 per million output tokens, 1.3x apart.
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 4.8BarsClaude Opus 5.5Ties
Coding014
Intelligence02
Agentic work115
Reasoning112
Math06
Knowledge16
Web design08
General125
All shared boards488
CodingLike-for-likeSix of these boards feed the Vibe Coding Index014
Coding benchmarks for Claude Opus 4.8 and Claude Opus 5.5
BenchmarkClaude Opus 4.8Claude Opus 5.5Leader
LiveBench coding77.3%96.3%Claude Opus 5.5
LMArena WebDev15561807Claude Opus 5.5
AA Coding Index74.3Not measuredOnly Claude Opus 4.8 measured
LiveCodeBench (Vals AI)87.8%Not measuredOnly Claude Opus 4.8 measured
SWE-bench Verified (Vals AI)88.6%Not measuredOnly Claude Opus 4.8 measured
Terminal-Bench 4 (Vals AI)23.2%65.2%Claude Opus 5.5
Vibe Code Bench (Vals AI)82.7%90.3%Claude Opus 5.5
Code migration (Vals AI)47.3%66.7%Claude Opus 5.5
ProgramBench (Vals AI)1.0%18.5%Claude Opus 5.5
IOI (Vals AI)Not measured95.1%Only Claude Opus 5.5 measured
Terminal-Bench 2.1 (Vals AI)71.9%87.6%Claude Opus 5.5
SWE-bench Multimodal (Vals AI)Not measured70.2%Only Claude Opus 5.5 measured
Vibe Code Bench 1-100 (Vals AI)Not measured30.4%Only Claude Opus 5.5 measured
SkillsBench (Vals AI)59.2%Not measuredOnly Claude Opus 4.8 measured
CyberBench (Vals AI)Not measured74.6%Only Claude Opus 5.5 measured
SciCode54.4%66.9%Claude Opus 5.5
Terminal-Bench Hard (Artificial Analysis run)58.3%Not measuredOnly Claude Opus 4.8 measured
FrontierCode46.5%54.6%Claude Opus 5.5
FrontierSWENot measured62.3%Only Claude Opus 5.5 measured
GSO-Bench47.1%Not measuredOnly Claude Opus 4.8 measured
WeirdML82.9%Not measuredOnly Claude Opus 4.8 measured
MirrorCodeNot measured77.4%Only Claude Opus 5.5 measured
ALE-BenchNot measured2147.4Only Claude Opus 5.5 measured
LMArena Text: coding14901545Claude Opus 5.5
LMArena Text: software and IT14881538Claude Opus 5.5
LMArena WebDev: React15571855Claude Opus 5.5
LMArena WebDev: HTML15431753Claude Opus 5.5
LMArena WebDev: from an imageNot measured1753Only Claude Opus 5.5 measured
SciCode12.3%18.5%Claude Opus 5.5
Neither model has a result on the other 10 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Opus 4.8 and Claude Opus 5.5
BenchmarkClaude Opus 4.8Claude Opus 5.5Leader
AA Intelligence Index41.857.6Claude Opus 5.5
Epoch Capabilities Index159.0168.8Claude Opus 5.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index115
Agentic work benchmarks for Claude Opus 4.8 and Claude Opus 5.5
BenchmarkClaude Opus 4.8Claude Opus 5.5Leader
AA Agentic Index41.9Not measuredOnly Claude Opus 4.8 measured
Design Arena: agents building web apps12331316Claude Opus 5.5
Design Arena: agents building full-stack apps1249Not measuredOnly Claude Opus 4.8 measured
Design Arena: agents building mobile apps12231309Claude Opus 5.5
Design Arena: agents building Android apps1233Not measuredOnly Claude Opus 4.8 measured
Design Arena: agents building Godot games1231Not measuredOnly Claude Opus 4.8 measured
Design Arena: agents building games1239Not measuredOnly Claude Opus 4.8 measured
Design Arena: HTML slides1171Not measuredOnly Claude Opus 4.8 measured
Design Arena: PowerPoint slides1204Not measuredOnly Claude Opus 4.8 measured
Design Arena: spreadsheets13111386Claude Opus 5.5
LiveBench research81.8%85.0%Claude Opus 5.5
LiveBench browser96.0%80.0%Claude Opus 4.8
LiveBench long agentic48.3%85.0%Claude Opus 5.5
SREBench (Vals AI)Not measured33.6%Only Claude Opus 5.5 measured
Finance Agent (Vals AI)53.9%58.6%Claude Opus 5.5
Tax Agent Bench (Vals AI)30.0%45.6%Claude Opus 5.5
Legal Research Bench (Vals AI)43.8%50.5%Claude Opus 5.5
Harvey's Legal Agent Benchmark (Vals AI)Not measured9.2%Only Claude Opus 5.5 measured
Excel Modeling Benchmark (Vals AI)69.4%75.9%Claude Opus 5.5
BioMysteryBench (Vals AI)Not measured79.3%Only Claude Opus 5.5 measured
Terminal-Bench-Science (Vals AI)4.3%47.1%Claude Opus 5.5
Vals Science IndexNot measured58.7%Only Claude Opus 5.5 measured
Time Horizon Index (Vals AI)11.8%91.3%Claude Opus 5.5
CUA-bench (Vals AI)Not measured14.0%Only Claude Opus 5.5 measured
Robo-bench (Vals AI)Not measured14.6%Only Claude Opus 5.5 measured
τ²-Bench Telecom94.4%Not measuredOnly Claude Opus 4.8 measured
APEX-Agents48.9%73.5%Claude Opus 5.5
Remote Labor Index8.3%21.3%Claude Opus 5.5
OSWorld 2.020.6%Not measuredOnly Claude Opus 4.8 measured
DeepResearch Bench50.2%Not measuredOnly Claude Opus 4.8 measured
PostTrainBench33.8%Not measuredOnly Claude Opus 4.8 measured
SpireClimbNot measured3.3%Only Claude Opus 5.5 measured
Vending-Bench 2$5,787$9,235Claude Opus 5.5
LMArena Search12041213Claude Opus 5.5
Neither model has a result on the other 7 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index112
Reasoning benchmarks for Claude Opus 4.8 and Claude Opus 5.5
BenchmarkClaude Opus 4.8Claude Opus 5.5Leader
GPQA Diamond92.4%Not measuredOnly Claude Opus 4.8 measured
LiveBench reasoning89.2%92.2%Claude Opus 5.5
MysteryMechanism (Vals AI)Not measured49.5%Only Claude Opus 5.5 measured
MMMU Pro (Vals AI)86.6%Not measuredOnly Claude Opus 4.8 measured
GPQA Diamond (Artificial Analysis run)92.0%Not measuredOnly Claude Opus 4.8 measured
Humanity's Last Exam (Artificial Analysis run)48.7%61.4%Claude Opus 5.5
GPQA Diamond (Epoch AI run)91.0%90.6%Claude Opus 4.8
ARC-AGI92.5%98.5%Claude Opus 5.5
ARC-AGI-272.1%93.3%Claude Opus 5.5
SimpleBench64.8%Not measuredOnly Claude Opus 4.8 measured
Chess puzzles52.0%67.0%Claude Opus 5.5
Mystery game puzzles36.0%71.0%Claude Opus 5.5
EBR-bench28.6%71.4%Claude Opus 5.5
LMArena Text: hard prompts14821536Claude Opus 5.5
LMArena Text: expert15031549Claude Opus 5.5
LMArena Text: hard prompts in English14871535Claude Opus 5.5
LMArena Vision: diagrams13151345Claude Opus 5.5
LMArena Vision: homework13371362Claude Opus 5.5
Kagi LLM Benchmark88.8%Not measuredOnly Claude Opus 4.8 measured
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 4.8 and Claude Opus 5.5
BenchmarkClaude Opus 4.8Claude Opus 5.5Leader
OTIS Mock AIME98.3%100.0%Claude Opus 5.5
FrontierMath, tiers 1 to 380.0%91.2%Claude Opus 5.5
FrontierMath, tier 456.1%95.0%Claude Opus 5.5
ProofBench69.0%100.0%Claude Opus 5.5
LMArena Text: math14861518Claude Opus 5.5
LMArena Text: mathematical work14971516Claude Opus 5.5
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index16
Knowledge benchmarks for Claude Opus 4.8 and Claude Opus 5.5
BenchmarkClaude Opus 4.8Claude Opus 5.5Leader
MMLU Pro89.6%Not measuredOnly Claude Opus 4.8 measured
LegalBench (Vals AI)83.6%Not measuredOnly Claude Opus 4.8 measured
CorpFin (Vals AI)66.7%Not measuredOnly Claude Opus 4.8 measured
TaxEval (Vals AI)75.6%Not measuredOnly Claude Opus 4.8 measured
MortgageTax (Vals AI)69.9%Not measuredOnly Claude Opus 4.8 measured
MedCode (Vals AI)53.2%49.8%Claude Opus 4.8
SimpleQA Verified53.0%72.2%Claude Opus 5.5
LMArena Text: science14771524Claude Opus 5.5
LMArena Text: medicine and healthcare14641509Claude Opus 5.5
LMArena Text: legal and government14771518Claude Opus 5.5
LMArena Text: business and finance14581494Claude Opus 5.5
FACTS Benchmark Suite53.5%65.3%Claude Opus 5.5
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index08
Web design benchmarks for Claude Opus 4.8 and Claude Opus 5.5
BenchmarkClaude Opus 4.8Claude Opus 5.5Leader
Design Arena: websites12581335Claude Opus 5.5
Design Arena: UI components12551382Claude Opus 5.5
Design Arena: game dev12641455Claude Opus 5.5
Design Arena: data viz12401398Claude Opus 5.5
Design Arena: 3D12221476Claude Opus 5.5
Design Arena: all code categories12551388Claude Opus 5.5
Design Arena: SVG11941328Claude Opus 5.5
Design Arena: ASCII art1277Not measuredOnly Claude Opus 4.8 measured
LiveBench design78.8%86.9%Claude Opus 5.5
GeneralLike-for-likePublic boards, shown as published, kept out of the index125
General benchmarks for Claude Opus 4.8 and Claude Opus 5.5
BenchmarkClaude Opus 4.8Claude Opus 5.5Leader
Vals IndexNot measured70.2%Only Claude Opus 5.5 measured
LiveBench data analysis66.0%80.3%Claude Opus 5.5
Public Benefits Bench (Vals AI)68.1%70.6%Claude Opus 5.5
SAGE (Vals AI)54.8%45.8%Claude Opus 4.8
MedScribe (Vals AI)85.8%91.4%Claude Opus 5.5
Vals Multimodal Index70.9%Not measuredOnly Claude Opus 4.8 measured
IFBench62.2%Not measuredOnly Claude Opus 4.8 measured
Long context reasoning (AA-LCR)77.7%84.7%Claude Opus 5.5
DTBench94.9%98.9%Claude Opus 5.5
LMCA57.5%68.2%Claude Opus 5.5
Surface Evolver Bench87.5%Not measuredOnly Claude Opus 4.8 measured
Furniture assembly42.5%83.3%Claude Opus 5.5
LMArena Text14611516Claude Opus 5.5
LMArena Text: instruction following14761537Claude Opus 5.5
LMArena Text: creative writing14541535Claude Opus 5.5
LMArena Vision12941321Claude Opus 5.5
LMArena Text: English14681519Claude Opus 5.5
LMArena Text: non-English14501507Claude Opus 5.5
LMArena Text: Chinese15061582Claude Opus 5.5
LMArena Text: German1472Not measuredOnly Claude Opus 4.8 measured
LMArena Text: Japanese14421534Claude Opus 5.5
LMArena Text: Korean1431Not measuredOnly Claude Opus 4.8 measured
LMArena Text: French14811493Claude Opus 5.5
LMArena Text: Spanish14651508Claude Opus 5.5
LMArena Text: Russian14741517Claude Opus 5.5
LMArena Text: Polish1459Not measuredOnly Claude Opus 4.8 measured
LMArena Text: multi-turn14761501Claude Opus 5.5
LMArena Text: longer queries14831532Claude Opus 5.5
LMArena Text: writing and language14611532Claude Opus 5.5
LMArena Text: entertainment and media14401515Claude Opus 5.5
LMArena Vision: English12931317Claude Opus 5.5
LMArena Vision: Chinese1346Not measuredOnly Claude Opus 4.8 measured
LMArena Vision: reading text13031326Claude Opus 5.5
LMArena Vision: humor1282Not measuredOnly Claude Opus 4.8 measured
LMArena Vision: creative writing13011320Claude Opus 5.5
LMArena Document1475Not measuredOnly Claude Opus 4.8 measured
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 4.8 and Claude Opus 5.5
BenchmarkClaude Opus 4.8Claude Opus 5.5Leader
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 4.8$0.018Fits in one request
Claude Opus 5.5$0.014Fits in one request

Claude Opus 5.5 costs less

Repository review

50K input + 3K output tokens

Claude Opus 4.8$0.325Fits in one request
Claude Opus 5.5$0.260Fits in one request

Claude Opus 5.5 costs less

Agent loop

200K input + 10K output tokens

Claude Opus 4.8$1.25Fits in one request
Claude Opus 5.5$1.00Fits in one request

Claude Opus 5.5 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 4.8 and Claude Opus 5.5
SpecificationAnthropic Claude Opus 4.8Anthropic Claude Opus 5.5
MakerAnthropicAnthropic
WeightsNo public weights listedNo public weights listed
ReleasedMay 27, 2026September 22, 2026
Context window1M1M
Input $/Mtok$5.00$4.00
Output $/Mtok$25.00$20.00
Coding index65.088.8
Independent measurements behind it65
Cost per solved task$2.17Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.8 better than Claude Opus 5.5 for coding?

Pick Claude Opus 5.5 for coding: it scores 88.8 on the Vibe Coding Index against 65.0 for Claude Opus 4.8, though on 5 benchmarks against 6. Pick Claude Opus 4.8 for work measured by LiveBench browser or GPQA Diamond (Epoch AI run), where it leads.

Which is cheaper, Claude Opus 4.8 or Claude Opus 5.5?

Claude Opus 4.8 costs $5.00 per million input tokens and $25.00 per million output tokens; Claude Opus 5.5 costs $4.00 and $20.00. Cost per solved task is known for Claude Opus 4.8 only.

Which has the bigger context window, Claude Opus 4.8 or Claude Opus 5.5?

Neither: both take 1M tokens.

How many benchmarks is the Claude Opus 4.8 vs Claude Opus 5.5 comparison based on?

92 benchmarks have a result for both models as of October 22, 2026. Claude Opus 4.8's coding index rests on 6 independent benchmarks and Claude Opus 5.5's on 5. 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-4-8-vs-claude-opus-5-5" title="Claude Opus 4.8 vs Claude Opus 5.5, 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-4-8-vs-claude-opus-5-5">LLMBenchmark.ai, Claude Opus 4.8 vs Claude Opus 5.5</a></p>