Enter opens the highlighted result. Esc closes.

Claude Opus 4.6 vs Claude Opus 4.8

Claude Opus 4.8 leads Claude Opus 4.6 on coding, 65.0 to 57.2 on the Vibe Coding Index, at about the same output price ($25.00 vs $25.00 per million). Updated October 22, 2026; 98 benchmarks have a result for both.

Replace Claude Opus 4.6 Replace Claude Opus 4.8
Claude Opus 4.6Anthropic
Coding
57.2
Overall
66.0
Output $/M
$25.00
53
Claude Opus 4.8Anthropic
Coding
65.0
Overall
69.8
Output $/M
$25.00
45
vs boards won of 98 shared

Claude Opus 4.6 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 57.2 for Claude Opus 4.6.

Pick Claude Opus 4.6 for a lower cost per solved task ($1.56 against $2.17) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.

Model AClaude Opus 4.6Anthropic57.2/1004 independent benchmarks$1.56 per solved taskModel BClaude Opus 4.8Anthropic65.0/1006 independent benchmarks$2.17 per solved task
Shared results
98
Claude Opus 4.6 only
12
Claude Opus 4.8 only
32
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 4.6 57.2 from 4 benchmarks, Claude Opus 4.8 65.0 from 6 benchmarks.
Widest category
Math, 12.7 points apart on average over 6 shared benchmarks.
Widest single gap
Chess puzzles: Claude Opus 4.6 21.0% against Claude Opus 4.8 52.0%, 31.0 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 4.6BarsClaude Opus 4.8Ties
Coding39
Intelligence02
Agentic work28
Reasoning611
Math24
Knowledge75
Web design71
General265
All shared boards5345
CodingLike-for-likeSix of these boards feed the Vibe Coding Index39
Coding benchmarks for Claude Opus 4.6 and Claude Opus 4.8
BenchmarkClaude Opus 4.6Claude Opus 4.8Leader
SWE-bench Verified75.6%Not measuredOnly Claude Opus 4.6 measured
SWE-bench Multilingual72.0%Not measuredOnly Claude Opus 4.6 measured
LiveBench codingNot measured77.3%Only Claude Opus 4.8 measured
LMArena WebDev15471556Claude Opus 4.8
AA Coding IndexNot measured74.3Only Claude Opus 4.8 measured
LiveCodeBench (Vals AI)84.7%87.8%Claude Opus 4.8
SWE-bench Verified (Vals AI)78.2%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)57.6%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
SciCodeNot measured54.4%Only Claude Opus 4.8 measured
Terminal-Bench Hard (Artificial Analysis run)48.5%58.3%Claude Opus 4.8
Terminal-Bench79.8%Not measuredOnly Claude Opus 4.6 measured
FrontierCode26.6%46.5%Claude Opus 4.8
GSO-Bench41.2%47.1%Claude Opus 4.8
WeirdML78.0%82.9%Claude Opus 4.8
Cybench93.0%Not measuredOnly Claude Opus 4.6 measured
LMArena Text: coding15341490Claude Opus 4.6
LMArena Text: software and IT15271488Claude Opus 4.6
LMArena WebDev: React15391557Claude Opus 4.8
LMArena WebDev: HTML15591543Claude Opus 4.6
LMArena WebDev: from an image1543Not measuredOnly Claude Opus 4.6 measured
SciCodeNot measured12.3%Only Claude Opus 4.8 measured
Neither model has a result on the other 13 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Opus 4.6 and Claude Opus 4.8
BenchmarkClaude Opus 4.6Claude Opus 4.8Leader
AA Intelligence Index31.941.8Claude Opus 4.8
Epoch Capabilities Index155.7159.0Claude Opus 4.8
Agentic workLike-for-likePublic boards, shown as published, kept out of the index28
Agentic work benchmarks for Claude Opus 4.6 and Claude Opus 4.8
BenchmarkClaude Opus 4.6Claude Opus 4.8Leader
AA Agentic IndexNot measured41.9Only Claude Opus 4.8 measured
Design Arena: agents building web apps12061233Claude Opus 4.8
Design Arena: agents building full-stack apps12201249Claude Opus 4.8
Design Arena: agents building mobile apps12071222Claude Opus 4.8
Design Arena: agents building Android apps11971233Claude Opus 4.8
Design Arena: agents building Godot gamesNot measured1231Only Claude Opus 4.8 measured
Design Arena: agents building games12121239Claude Opus 4.8
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 Telecom92.1%94.4%Claude Opus 4.8
APEX-Agents46.3%48.9%Claude Opus 4.8
METR time horizons78.9%Not measuredOnly Claude Opus 4.6 measured
Remote Labor Index4.2%8.3%Claude Opus 4.8
OSWorld 2.0Not measured20.6%Only Claude Opus 4.8 measured
DeepResearch Bench55.3%50.2%Claude Opus 4.6
PostTrainBenchNot measured33.8%Only Claude Opus 4.8 measured
Vending-Bench 2$8,018$5,787Claude Opus 4.6
LMArena SearchNot measured1204Only Claude Opus 4.8 measured
Neither model has a result on the other 13 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index611
Reasoning benchmarks for Claude Opus 4.6 and Claude Opus 4.8
BenchmarkClaude Opus 4.6Claude Opus 4.8Leader
GPQA Diamond89.7%92.4%Claude Opus 4.8
LiveBench reasoningNot measured89.2%Only Claude Opus 4.8 measured
MMMU Pro (Vals AI)83.9%86.6%Claude Opus 4.8
GPQA Diamond (Artificial Analysis run)89.6%92.0%Claude Opus 4.8
Humanity's Last Exam (Artificial Analysis run)39.9%48.7%Claude Opus 4.8
GPQA Diamond (Epoch AI run)90.5%91.0%Claude Opus 4.8
ARC-AGI94.0%92.5%Claude Opus 4.6
ARC-AGI-269.2%72.1%Claude Opus 4.8
SimpleBench67.6%64.8%Claude Opus 4.6
Chess puzzles21.0%52.0%Claude Opus 4.8
Mystery game puzzles25.0%36.0%Claude Opus 4.8
EBR-bench12.7%28.6%Claude Opus 4.8
LMArena Text: hard prompts15251482Claude Opus 4.6
LMArena Text: expert15441503Claude Opus 4.6
LMArena Text: hard prompts in English15301487Claude Opus 4.6
LMArena Vision: diagrams13401315Claude Opus 4.6
LMArena Vision: homework13371337Claude Opus 4.8
Kagi LLM Benchmark83.6%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 4.6 and Claude Opus 4.8
BenchmarkClaude Opus 4.6Claude Opus 4.8Leader
AIME95.6%Not measuredOnly Claude Opus 4.6 measured
OTIS Mock AIME94.4%98.3%Claude Opus 4.8
FrontierMath, tiers 1 to 366.0%80.0%Claude Opus 4.8
FrontierMath, tier 426.8%56.1%Claude Opus 4.8
ProofBench50.0%69.0%Claude Opus 4.8
LMArena Text: math15181486Claude Opus 4.6
LMArena Text: mathematical work15251497Claude Opus 4.6
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index75
Knowledge benchmarks for Claude Opus 4.6 and Claude Opus 4.8
BenchmarkClaude Opus 4.6Claude Opus 4.8Leader
MMLU Pro89.1%89.6%Claude Opus 4.8
LegalBench (Vals AI)85.3%83.6%Claude Opus 4.6
CaseLaw (Vals AI)62.1%Not measuredOnly Claude Opus 4.6 measured
CorpFin (Vals AI)67.0%66.7%Claude Opus 4.6
TaxEval (Vals AI)76.0%75.6%Claude Opus 4.6
MortgageTax (Vals AI)68.5%69.9%Claude Opus 4.8
MedQA (Vals AI)95.4%Not measuredOnly Claude Opus 4.6 measured
MedCode (Vals AI)49.1%53.2%Claude Opus 4.8
SimpleQA Verified47.0%53.0%Claude Opus 4.8
LMArena Text: science15191477Claude Opus 4.6
LMArena Text: medicine and healthcare15041464Claude Opus 4.6
LMArena Text: legal and government15121477Claude Opus 4.6
LMArena Text: business and finance14971458Claude Opus 4.6
FACTS Benchmark Suite41.5%53.5%Claude Opus 4.8
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index71
Web design benchmarks for Claude Opus 4.6 and Claude Opus 4.8
BenchmarkClaude Opus 4.6Claude Opus 4.8Leader
Design Arena: websites12911258Claude Opus 4.6
Design Arena: UI components12811255Claude Opus 4.6
Design Arena: game dev12771264Claude Opus 4.6
Design Arena: data viz12791240Claude Opus 4.6
Design Arena: 3D12731222Claude Opus 4.6
Design Arena: all code categories12881255Claude Opus 4.6
Design Arena: SVG12271195Claude Opus 4.6
Design Arena: ASCII art12551277Claude Opus 4.8
LiveBench designNot measured78.8%Only Claude Opus 4.8 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index265
General benchmarks for Claude Opus 4.6 and Claude Opus 4.8
BenchmarkClaude Opus 4.6Claude 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)51.6%54.8%Claude Opus 4.8
MedScribe (Vals AI)86.7%85.8%Claude Opus 4.6
Vals Multimodal IndexNot measured70.9%Only Claude Opus 4.8 measured
IFBench53.1%62.2%Claude Opus 4.8
Long context reasoning (AA-LCR)78.0%77.7%Claude Opus 4.6
DTBench91.2%94.9%Claude Opus 4.8
LMCA55.8%57.5%Claude Opus 4.8
CL-bench20.7%Not measuredOnly Claude Opus 4.6 measured
Surface Evolver BenchNot measured87.5%Only Claude Opus 4.8 measured
Furniture assembly28.3%42.5%Claude Opus 4.8
CL-bench Life17.0%Not measuredOnly Claude Opus 4.6 measured
LMArena Text15011461Claude Opus 4.6
LMArena Text: instruction following15211476Claude Opus 4.6
LMArena Text: creative writing15051454Claude Opus 4.6
LMArena Vision13161294Claude Opus 4.6
LMArena Text: English15111468Claude Opus 4.6
LMArena Text: non-English14881450Claude Opus 4.6
LMArena Text: Chinese15511506Claude Opus 4.6
LMArena Text: German15001472Claude Opus 4.6
LMArena Text: Japanese14881442Claude Opus 4.6
LMArena Text: Korean14641431Claude Opus 4.6
LMArena Text: French15121481Claude Opus 4.6
LMArena Text: Spanish15101465Claude Opus 4.6
LMArena Text: Russian14971474Claude Opus 4.6
LMArena Text: Polish14991459Claude Opus 4.6
LMArena Text: multi-turn15111476Claude Opus 4.6
LMArena Text: longer queries15181483Claude Opus 4.6
LMArena Text: writing and language15021461Claude Opus 4.6
LMArena Text: entertainment and media14921440Claude Opus 4.6
LMArena Vision: English13241293Claude Opus 4.6
LMArena Vision: Chinese13701346Claude Opus 4.6
LMArena Vision: reading text13261303Claude Opus 4.6
LMArena Vision: humor13141282Claude Opus 4.6
LMArena Vision: recognizing things1274Not measuredOnly Claude Opus 4.6 measured
LMArena Vision: creative writing13311301Claude Opus 4.6
LMArena Document15071475Claude Opus 4.6
Neither model has a result on the other 8 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Opus 4.6 and Claude Opus 4.8
BenchmarkClaude Opus 4.6Claude 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 4.6$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 4.6$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 4.6$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 4.6 and Claude Opus 4.8
SpecificationAnthropic Claude Opus 4.6Anthropic Claude Opus 4.8
MakerAnthropicAnthropic
WeightsNo public weights listedNo public weights listed
ReleasedFebruary 4, 2026May 27, 2026
Context window1M1M
Input $/Mtok$5.00$5.00
Output $/Mtok$25.00$25.00
Coding index57.265.0
Independent measurements behind it46
Cost per solved task$1.56$2.17
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.6 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 57.2 for Claude Opus 4.6. Pick Claude Opus 4.6 for a lower cost per solved task ($1.56 against $2.17) and work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.

Which is cheaper, Claude Opus 4.6 or Claude Opus 4.8?

Claude Opus 4.6 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 4.6 costs $1.56 and Claude Opus 4.8 $2.17.

Which has the bigger context window, Claude Opus 4.6 or Claude Opus 4.8?

Neither: both take 1M tokens.

How many benchmarks is the Claude Opus 4.6 vs Claude Opus 4.8 comparison based on?

98 benchmarks have a result for both models as of October 22, 2026. Claude Opus 4.6'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-4-6-vs-claude-opus-4-8" title="Claude Opus 4.6 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-4-6-vs-claude-opus-4-8">LLMBenchmark.ai, Claude Opus 4.6 vs Claude Opus 4.8</a></p>