Enter opens the highlighted result. Esc closes.

Claude Opus 4.8 vs Claude Sonnet 4.6

Updated October 21, 2026. 109 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Opus 4.8 Replace Claude Sonnet 4.6
Claude Opus 4.8Anthropic
Coding
66.0
Overall
41.8
Output $/M
$25.00
90
Claude Sonnet 4.6Anthropic
Coding
57.8
Overall
30.1
Output $/M
$15.00
19
vs boards won of 109 shared

Decision reading

Pick Claude Opus 4.8 for coding: it scores 66.0 on the Vibe Coding Index against 57.8 for Claude Sonnet 4.6.

Pick Claude Sonnet 4.6 when output tokens cost 1.7x less, or when a solved task costs $1.68 against $2.17.

Model AClaude Opus 4.8Anthropic66.0/1002 independent benchmarks$2.17 per solved taskModel BClaude Sonnet 4.6Anthropic57.8/1002 independent benchmarks$1.68 per solved task
Shared results
109
Claude Opus 4.8 only
17
Claude Sonnet 4.6 only
8
Like-for-like categories
8 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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 66.0 from 2 benchmarks, Claude Sonnet 4.6 57.8 from 2 benchmarks.
Widest category
Math, 10.7 points apart on average over 4 shared benchmarks.
Widest single gap
Chess puzzles: Claude Opus 4.8 52.0% against Claude Sonnet 4.6 23.0%, 29.0 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.8 $25.00 against Claude Sonnet 4.6 $15.00 per million output tokens, 1.7x 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 Sonnet 4.6Ties
Coding162
Intelligence20
Agentic work172
Reasoning132
Math40
Knowledge82
Web design36
General275
All shared boards9019
CodingLike-for-likeFour of these boards feed the Vibe Coding Index162
Coding benchmarks for Claude Opus 4.8 and Claude Sonnet 4.6
BenchmarkClaude Opus 4.8Claude Sonnet 4.6Leader
LiveBench coding77.3%66.6%Claude Opus 4.8
LMArena WebDev15561523Claude Opus 4.8
AA Coding Index74.363.0Claude Opus 4.8
LiveCodeBench (Vals AI)87.8%82.1%Claude Opus 4.8
SWE-bench Verified (Vals AI)88.6%77.4%Claude Opus 4.8
Terminal-Bench 4 (Vals AI)23.2%Not measuredOnly Claude Opus 4.8 measured
Vibe Code Bench (Vals AI)82.7%55.8%Claude Opus 4.8
Code migration (Vals AI)47.3%39.9%Claude Opus 4.8
ProgramBench (Vals AI)1.0%0.5%Claude Opus 4.8
Terminal-Bench 2.1 (Vals AI)71.9%57.3%Claude Opus 4.8
SkillsBench (Vals AI)59.2%49.0%Claude Opus 4.8
SciCode54.4%50.1%Claude Opus 4.8
Terminal-Bench Hard (Artificial Analysis run)58.3%53.0%Claude Opus 4.8
Terminal-BenchNot measured53.4%Only Claude Sonnet 4.6 measured
FrontierCode46.5%24.3%Claude Opus 4.8
GSO-Bench47.1%Not measuredOnly Claude Opus 4.8 measured
WeirdML82.9%66.1%Claude Opus 4.8
LMArena Text: coding14901503Claude Sonnet 4.6
LMArena Text: software and IT14881491Claude Sonnet 4.6
LMArena WebDev: React15571512Claude Opus 4.8
LMArena WebDev: HTML15431527Claude Opus 4.8
LMArena WebDev: from an imageNot measured1529Only Claude Sonnet 4.6 measured
Neither model has a result on the other 16 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Opus 4.8 and Claude Sonnet 4.6
BenchmarkClaude Opus 4.8Claude Sonnet 4.6Leader
AA Intelligence Index41.830.1Claude Opus 4.8
Epoch Capabilities Index159.0152.8Claude Opus 4.8
Agentic workLike-for-likePublic boards, shown as published, kept out of the index172
Agentic work benchmarks for Claude Opus 4.8 and Claude Sonnet 4.6
BenchmarkClaude Opus 4.8Claude Sonnet 4.6Leader
AA Agentic Index41.931.8Claude Opus 4.8
Design Arena: agents building web apps12331190Claude Opus 4.8
Design Arena: agents building full-stack apps12491213Claude Opus 4.8
Design Arena: agents building mobile apps12221212Claude Opus 4.8
Design Arena: agents building Android apps12371202Claude Opus 4.8
Design Arena: agents building Godot games12311226Claude Opus 4.8
Design Arena: agents building games12381177Claude Opus 4.8
Design Arena: HTML slides1221Not measuredOnly Claude Opus 4.8 measured
Design Arena: PowerPoint slides1227Not measuredOnly Claude Opus 4.8 measured
LiveBench research81.8%63.6%Claude Opus 4.8
LiveBench browser96.0%68.0%Claude Opus 4.8
LiveBench long agentic48.3%23.1%Claude Opus 4.8
Finance Agent (Vals AI)53.9%51.0%Claude Opus 4.8
Tax Agent Bench (Vals AI)30.0%25.8%Claude Opus 4.8
Legal Research Bench (Vals AI)43.8%38.5%Claude Opus 4.8
Excel Modeling Benchmark (Vals AI)69.4%60.2%Claude Opus 4.8
Terminal-Bench-Science (Vals AI)4.3%Not measuredOnly Claude Opus 4.8 measured
Time Horizon Index (Vals AI)11.8%Not measuredOnly Claude Opus 4.8 measured
τ²-Bench Telecom94.4%79.5%Claude Opus 4.8
APEX-Agents48.9%43.0%Claude Opus 4.8
Remote Labor Index8.3%Not measuredOnly Claude Opus 4.8 measured
OSWorld 2.020.6%9.3%Claude Opus 4.8
DeepResearch Bench50.2%54.9%Claude Sonnet 4.6
PostTrainBench33.8%Not measuredOnly Claude Opus 4.8 measured
OSWorldNot measured72.1%Only Claude Sonnet 4.6 measured
Vending-Bench 2$5,787$7,204Claude Sonnet 4.6
LMArena Search1204Not measuredOnly Claude Opus 4.8 measured
Neither model has a result on the other 12 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index132
Reasoning benchmarks for Claude Opus 4.8 and Claude Sonnet 4.6
BenchmarkClaude Opus 4.8Claude Sonnet 4.6Leader
GPQA Diamond92.4%85.6%Claude Opus 4.8
LiveBench reasoning89.2%86.4%Claude Opus 4.8
MMMU Pro (Vals AI)86.6%83.6%Claude Opus 4.8
GPQA Diamond (Artificial Analysis run)92.0%87.5%Claude Opus 4.8
Humanity's Last Exam (Artificial Analysis run)48.7%33.6%Claude Opus 4.8
GPQA Diamond (Epoch AI run)91.0%87.4%Claude Opus 4.8
ARC-AGI92.5%86.5%Claude Opus 4.8
ARC-AGI-272.1%60.4%Claude Opus 4.8
SimpleBench64.8%Not measuredOnly Claude Opus 4.8 measured
Chess puzzles52.0%23.0%Claude Opus 4.8
Mystery game puzzles36.0%16.0%Claude Opus 4.8
EBR-bench28.6%Not measuredOnly Claude Opus 4.8 measured
LMArena Text: hard prompts14821485Claude Sonnet 4.6
LMArena Text: expert15031500Claude Opus 4.8
LMArena Text: hard prompts in English14871493Claude Sonnet 4.6
LMArena Vision: diagrams13151306Claude Opus 4.8
LMArena Vision: homework13371311Claude 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 index40
Math benchmarks for Claude Opus 4.8 and Claude Sonnet 4.6
BenchmarkClaude Opus 4.8Claude Sonnet 4.6Leader
AIMENot measured92.3%Only Claude Sonnet 4.6 measured
OTIS Mock AIME98.3%85.8%Claude Opus 4.8
FrontierMath, tiers 1 to 380.0%Not measuredOnly Claude Opus 4.8 measured
FrontierMath, tier 456.1%Not measuredOnly Claude Opus 4.8 measured
ProofBench69.0%45.0%Claude Opus 4.8
LMArena Text: math14861462Claude Opus 4.8
LMArena Text: mathematical work14971483Claude Opus 4.8
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index82
Knowledge benchmarks for Claude Opus 4.8 and Claude Sonnet 4.6
BenchmarkClaude Opus 4.8Claude Sonnet 4.6Leader
MMLU Pro89.6%87.3%Claude Opus 4.8
LegalBench (Vals AI)83.6%82.1%Claude Opus 4.8
CaseLaw (Vals AI)Not measured64.0%Only Claude Sonnet 4.6 measured
CorpFin (Vals AI)66.7%65.3%Claude Opus 4.8
TaxEval (Vals AI)75.6%77.1%Claude Sonnet 4.6
MortgageTax (Vals AI)69.9%67.7%Claude Opus 4.8
MedQA (Vals AI)Not measured92.1%Only Claude Sonnet 4.6 measured
MedCode (Vals AI)53.2%Not measuredOnly Claude Opus 4.8 measured
SimpleQA Verified53.0%35.5%Claude Opus 4.8
LMArena Text: science14771474Claude Opus 4.8
LMArena Text: medicine and healthcare14641451Claude Opus 4.8
LMArena Text: legal and government14771470Claude Opus 4.8
LMArena Text: business and finance14581464Claude Sonnet 4.6
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index36
Web design benchmarks for Claude Opus 4.8 and Claude Sonnet 4.6
BenchmarkClaude Opus 4.8Claude Sonnet 4.6Leader
Design Arena: websites12581285Claude Sonnet 4.6
Design Arena: UI components12561271Claude Sonnet 4.6
Design Arena: game dev12641259Claude Opus 4.8
Design Arena: data viz12401278Claude Sonnet 4.6
Design Arena: 3D12231234Claude Sonnet 4.6
Design Arena: all code categories12551276Claude Sonnet 4.6
Design Arena: SVG11941196Claude Sonnet 4.6
Design Arena: ASCII art12761235Claude Opus 4.8
LiveBench design78.8%71.8%Claude Opus 4.8
GeneralLike-for-likePublic boards, shown as published, kept out of the index275
General benchmarks for Claude Opus 4.8 and Claude Sonnet 4.6
BenchmarkClaude Opus 4.8Claude Sonnet 4.6Leader
LiveBench data analysis66.0%76.1%Claude Sonnet 4.6
Public Benefits Bench (Vals AI)68.1%62.5%Claude Opus 4.8
SAGE (Vals AI)54.8%46.6%Claude Opus 4.8
MedScribe (Vals AI)85.8%Not measuredOnly Claude Opus 4.8 measured
Vals Multimodal Index70.9%60.6%Claude Opus 4.8
IFBench62.2%56.6%Claude Opus 4.8
Long context reasoning (AA-LCR)77.7%80.0%Claude Sonnet 4.6
DTBench94.9%89.9%Claude Opus 4.8
LMCA57.5%46.5%Claude Opus 4.8
Surface Evolver Bench87.5%Not measuredOnly Claude Opus 4.8 measured
Furniture assembly42.5%Not measuredOnly Claude Opus 4.8 measured
ExploitBenchNot measured23.6%Only Claude Sonnet 4.6 measured
LMArena Text14611458Claude Opus 4.8
LMArena Text: instruction following14761476Claude Opus 4.8
LMArena Text: creative writing14541435Claude Opus 4.8
LMArena Vision12941283Claude Opus 4.8
LMArena Text: English14681472Claude Sonnet 4.6
LMArena Text: non-English14501440Claude Opus 4.8
LMArena Text: Chinese15061491Claude Opus 4.8
LMArena Text: German14721428Claude Opus 4.8
LMArena Text: Japanese14421420Claude Opus 4.8
LMArena Text: Korean14311410Claude Opus 4.8
LMArena Text: French14811465Claude Opus 4.8
LMArena Text: Spanish14651464Claude Opus 4.8
LMArena Text: Russian14741440Claude Opus 4.8
LMArena Text: Polish14591443Claude Opus 4.8
LMArena Text: multi-turn14761464Claude Opus 4.8
LMArena Text: longer queries14831479Claude Opus 4.8
LMArena Text: writing and language14611444Claude Opus 4.8
LMArena Text: entertainment and media14401431Claude Opus 4.8
LMArena Vision: English12931298Claude Sonnet 4.6
LMArena Vision: Chinese13461307Claude Opus 4.8
LMArena Vision: reading text13031296Claude Opus 4.8
LMArena Vision: humor12821248Claude Opus 4.8
LMArena Vision: recognizing thingsNot measured1195Only Claude Sonnet 4.6 measured
LMArena Vision: creative writing13011272Claude Opus 4.8
LMArena Document14751482Claude Sonnet 4.6
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 4.8 and Claude Sonnet 4.6
BenchmarkClaude Opus 4.8Claude Sonnet 4.6Leader
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 Sonnet 4.6$0.011Fits in one request

Claude Sonnet 4.6 costs less

Repository review

50K input + 3K output tokens

Claude Opus 4.8$0.325Fits in one request
Claude Sonnet 4.6$0.195Fits in one request

Claude Sonnet 4.6 costs less

Agent loop

200K input + 10K output tokens

Claude Opus 4.8$1.25Fits in one request
Claude Sonnet 4.6$0.750Fits in one request

Claude Sonnet 4.6 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 Sonnet 4.6
SpecificationAnthropic Claude Opus 4.8Anthropic Claude Sonnet 4.6
MakerAnthropicAnthropic
WeightsNo public weights listedNo public weights listed
ReleasedMay 27, 2026February 17, 2026
Context window1M1M
Input $/Mtok$5.00$3.00
Output $/Mtok$25.00$15.00
Coding index66.057.8
Independent measurements behind it22
Cost per solved task$2.17$1.68
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.8 better than Claude Sonnet 4.6 for coding?

Pick Claude Opus 4.8 for coding: it scores 66.0 on the Vibe Coding Index against 57.8 for Claude Sonnet 4.6. Pick Claude Sonnet 4.6 when output tokens cost 1.7x less, or when a solved task costs $1.68 against $2.17.

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

Claude Opus 4.8 costs $5.00 per million input tokens and $25.00 per million output tokens; Claude Sonnet 4.6 costs $3.00 and $15.00. Per solved SWE-bench Verified task, Claude Opus 4.8 costs $2.17 and Claude Sonnet 4.6 $1.68.

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

Neither: both take 1M tokens.

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

109 benchmarks have a result for both models as of October 21, 2026. Claude Opus 4.8's coding index rests on 2 independent benchmarks and Claude Sonnet 4.6's on 2. 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-sonnet-4-6" title="Claude Opus 4.8 vs Claude Sonnet 4.6, 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-sonnet-4-6">LLMBenchmark.ai, Claude Opus 4.8 vs Claude Sonnet 4.6</a></p>