LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Sonnet 4.5 vs Claude Sonnet 4.6

Updated October 21, 2026. 76 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Sonnet 4.5 Replace Claude Sonnet 4.6
Claude Sonnet 4.5Anthropic
Coding
59.1
Overall
20.7
Output $/M
$15.00
6
Claude Sonnet 4.6Anthropic
Coding
57.8
Overall
30.1
Output $/M
$15.00
70
vs boards won of 76 shared

Decision reading

Claude Sonnet 4.5 and Claude Sonnet 4.6 are level for coding, 59.1 against 57.8 on the Vibe Coding Index, so price and context decide.

Pick Claude Sonnet 4.6 when what matters is LMArena WebDev or AA Coding Index, where it leads. Pick Claude Sonnet 4.5 when a solved task costs $1.16 against $1.68, or when what matters is Mystery game puzzles or MMLU Pro, where it leads.

Model AClaude Sonnet 4.5Anthropic59.1/1002 independent benchmarks$1.16 per solved taskModel BClaude Sonnet 4.6Anthropic57.8/1002 independent benchmarks$1.68 per solved task
Shared results
76
Claude Sonnet 4.5 only
16
Claude Sonnet 4.6 only
41
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 Sonnet 4.5 59.1 from 2 benchmarks, Claude Sonnet 4.6 57.8 from 2 benchmarks.
Widest category
Coding, 13.9 points apart on average over 11 shared benchmarks.
Widest single gap
ARC-AGI-2: Claude Sonnet 4.5 13.6% against Claude Sonnet 4.6 60.4%, 46.8 points apart on a 0 to 100 scale.
Output price
Both cost $15.00 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 Sonnet 4.5BarsClaude Sonnet 4.6Ties
Coding011
Intelligence02
Agentic work07
Reasoning19
Math05
Knowledge39
Web design08
General219
All shared boards670
CodingLike-for-likeFour of these boards feed the Vibe Coding Index011
Coding benchmarks for Claude Sonnet 4.5 and Claude Sonnet 4.6
BenchmarkClaude Sonnet 4.5Claude Sonnet 4.6Leader
SWE-bench Verified74.8%Not measuredOnly Claude Sonnet 4.5 measured
SWE-bench Multilingual67.0%Not measuredOnly Claude Sonnet 4.5 measured
LiveBench codingNot measured66.6%Only Claude Sonnet 4.6 measured
LMArena WebDev13941523Claude Sonnet 4.6
AA Coding Index52.163.0Claude Sonnet 4.6
LiveCodeBench (Vals AI)73.0%82.1%Claude Sonnet 4.6
SWE-bench Verified (Vals AI)70.0%77.4%Claude Sonnet 4.6
Vibe Code Bench (Vals AI)22.6%55.8%Claude Sonnet 4.6
Code migration (Vals AI)Not measured39.9%Only Claude Sonnet 4.6 measured
ProgramBench (Vals AI)Not measured0.5%Only Claude Sonnet 4.6 measured
Terminal-Bench 2.1 (Vals AI)Not measured57.3%Only Claude Sonnet 4.6 measured
SkillsBench (Vals AI)Not measured49.0%Only Claude Sonnet 4.6 measured
SciCodeNot measured50.1%Only Claude Sonnet 4.6 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured53.0%Only Claude Sonnet 4.6 measured
Terminal-Bench46.5%53.4%Claude Sonnet 4.6
FrontierCodeNot measured24.3%Only Claude Sonnet 4.6 measured
GSO-Bench14.7%Not measuredOnly Claude Sonnet 4.5 measured
WeirdML47.7%66.1%Claude Sonnet 4.6
Cybench60.0%Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text: coding14881503Claude Sonnet 4.6
LMArena Text: software and IT14731491Claude Sonnet 4.6
LMArena WebDev: React13861512Claude Sonnet 4.6
LMArena WebDev: HTML13991527Claude Sonnet 4.6
LMArena WebDev: from an imageNot measured1529Only Claude Sonnet 4.6 measured
Neither model has a result on the other 14 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Sonnet 4.5 and Claude Sonnet 4.6
BenchmarkClaude Sonnet 4.5Claude Sonnet 4.6Leader
AA Intelligence Index20.730.1Claude Sonnet 4.6
Epoch Capabilities Index146.7152.8Claude Sonnet 4.6
Agentic workLike-for-likePublic boards, shown as published, kept out of the index07
Agentic work benchmarks for Claude Sonnet 4.5 and Claude Sonnet 4.6
BenchmarkClaude Sonnet 4.5Claude Sonnet 4.6Leader
AA Agentic Index15.831.8Claude Sonnet 4.6
Design Arena: agents building web apps10601190Claude Sonnet 4.6
Design Arena: agents building full-stack apps10501213Claude Sonnet 4.6
Design Arena: agents building mobile apps11371212Claude Sonnet 4.6
Design Arena: agents building Android appsNot measured1202Only Claude Sonnet 4.6 measured
Design Arena: agents building Godot gamesNot measured1226Only Claude Sonnet 4.6 measured
Design Arena: agents building gamesNot measured1177Only Claude Sonnet 4.6 measured
LiveBench researchNot measured63.6%Only Claude Sonnet 4.6 measured
LiveBench browserNot measured68.0%Only Claude Sonnet 4.6 measured
LiveBench long agenticNot measured23.1%Only Claude Sonnet 4.6 measured
Finance Agent (Vals AI)Not measured51.0%Only Claude Sonnet 4.6 measured
Tax Agent Bench (Vals AI)Not measured25.8%Only Claude Sonnet 4.6 measured
Legal Research Bench (Vals AI)Not measured38.5%Only Claude Sonnet 4.6 measured
Excel Modeling Benchmark (Vals AI)Not measured60.2%Only Claude Sonnet 4.6 measured
τ²-Bench TelecomNot measured79.5%Only Claude Sonnet 4.6 measured
APEX-AgentsNot measured43.0%Only Claude Sonnet 4.6 measured
METR time horizons67.4%Not measuredOnly Claude Sonnet 4.5 measured
Remote Labor Index2.1%Not measuredOnly Claude Sonnet 4.5 measured
GDPval42.5%Not measuredOnly Claude Sonnet 4.5 measured
OSWorld 2.0Not measured9.3%Only Claude Sonnet 4.6 measured
DeepResearch Bench52.6%54.9%Claude Sonnet 4.6
OSWorld62.9%72.1%Claude Sonnet 4.6
Vending-Bench 2$3,839$7,204Claude Sonnet 4.6
Neither model has a result on the other 16 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index19
Reasoning benchmarks for Claude Sonnet 4.5 and Claude Sonnet 4.6
BenchmarkClaude Sonnet 4.5Claude Sonnet 4.6Leader
GPQA Diamond81.6%85.6%Claude Sonnet 4.6
LiveBench reasoningNot measured86.4%Only Claude Sonnet 4.6 measured
MMMU Pro (Vals AI)79.3%83.6%Claude Sonnet 4.6
GPQA Diamond (Artificial Analysis run)Not measured87.5%Only Claude Sonnet 4.6 measured
Humanity's Last Exam (Artificial Analysis run)Not measured33.6%Only Claude Sonnet 4.6 measured
GPQA Diamond (Epoch AI run)82.3%87.4%Claude Sonnet 4.6
ARC-AGI63.7%86.5%Claude Sonnet 4.6
ARC-AGI-213.6%60.4%Claude Sonnet 4.6
SimpleBench54.3%Not measuredOnly Claude Sonnet 4.5 measured
Chess puzzles10.0%23.0%Claude Sonnet 4.6
Mystery game puzzles17.0%16.0%Claude Sonnet 4.5
EBR-bench2.4%Not measuredOnly Claude Sonnet 4.5 measured
VPCT39.8%Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text: hard prompts14621485Claude Sonnet 4.6
LMArena Text: expert14831500Claude Sonnet 4.6
LMArena Text: hard prompts in English14711493Claude Sonnet 4.6
LMArena Vision: diagramsNot measured1306Only Claude Sonnet 4.6 measured
LMArena Vision: homeworkNot measured1311Only Claude Sonnet 4.6 measured
Neither model has a result on the other 3 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index05
Math benchmarks for Claude Sonnet 4.5 and Claude Sonnet 4.6
BenchmarkClaude Sonnet 4.5Claude Sonnet 4.6Leader
AIME88.2%92.3%Claude Sonnet 4.6
MGSM (Vals AI)94.3%Not measuredOnly Claude Sonnet 4.5 measured
OTIS Mock AIME77.8%85.8%Claude Sonnet 4.6
FrontierMath, tiers 1 to 323.9%Not measuredOnly Claude Sonnet 4.5 measured
FrontierMath, tier 42.4%Not measuredOnly Claude Sonnet 4.5 measured
ProofBench19.0%45.0%Claude Sonnet 4.6
MATH level 597.7%Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text: math14491462Claude Sonnet 4.6
LMArena Text: mathematical work14621483Claude Sonnet 4.6
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index39
Knowledge benchmarks for Claude Sonnet 4.5 and Claude Sonnet 4.6
BenchmarkClaude Sonnet 4.5Claude Sonnet 4.6Leader
MMLU Pro87.4%87.3%Claude Sonnet 4.5
LegalBench (Vals AI)84.1%82.1%Claude Sonnet 4.5
CaseLaw (Vals AI)62.2%64.0%Claude Sonnet 4.6
CorpFin (Vals AI)62.0%65.3%Claude Sonnet 4.6
TaxEval (Vals AI)73.3%77.1%Claude Sonnet 4.6
MortgageTax (Vals AI)64.0%67.7%Claude Sonnet 4.6
MedQA (Vals AI)94.7%92.1%Claude Sonnet 4.5
MedCode (Vals AI)44.1%Not measuredOnly Claude Sonnet 4.5 measured
SimpleQA Verified30.7%35.5%Claude Sonnet 4.6
LMArena Text: science14481474Claude Sonnet 4.6
LMArena Text: medicine and healthcare14441451Claude Sonnet 4.6
LMArena Text: legal and government14511470Claude Sonnet 4.6
LMArena Text: business and finance14401464Claude 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 index08
Web design benchmarks for Claude Sonnet 4.5 and Claude Sonnet 4.6
BenchmarkClaude Sonnet 4.5Claude Sonnet 4.6Leader
Design Arena: websites11901285Claude Sonnet 4.6
Design Arena: UI components11731271Claude Sonnet 4.6
Design Arena: game dev11661259Claude Sonnet 4.6
Design Arena: data viz11671278Claude Sonnet 4.6
Design Arena: 3D11581234Claude Sonnet 4.6
Design Arena: all code categories11831276Claude Sonnet 4.6
Design Arena: SVG11141196Claude Sonnet 4.6
Design Arena: ASCII art12041235Claude Sonnet 4.6
LiveBench designNot measured71.8%Only Claude Sonnet 4.6 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index219
General benchmarks for Claude Sonnet 4.5 and Claude Sonnet 4.6
BenchmarkClaude Sonnet 4.5Claude Sonnet 4.6Leader
LiveBench data analysisNot measured76.1%Only Claude Sonnet 4.6 measured
Public Benefits Bench (Vals AI)Not measured62.5%Only Claude Sonnet 4.6 measured
SAGE (Vals AI)36.1%46.6%Claude Sonnet 4.6
MedScribe (Vals AI)84.5%Not measuredOnly Claude Sonnet 4.5 measured
Vals Multimodal IndexNot measured60.6%Only Claude Sonnet 4.6 measured
IFBenchNot measured56.6%Only Claude Sonnet 4.6 measured
Long context reasoning (AA-LCR)Not measured80.0%Only Claude Sonnet 4.6 measured
DTBench83.2%89.9%Claude Sonnet 4.6
LMCA38.8%46.5%Claude Sonnet 4.6
ExploitBenchNot measured23.6%Only Claude Sonnet 4.6 measured
LMArena Text14381458Claude Sonnet 4.6
LMArena Text: instruction following14591476Claude Sonnet 4.6
LMArena Text: creative writing14421435Claude Sonnet 4.5
LMArena VisionNot measured1283Only Claude Sonnet 4.6 measured
LMArena Text: English14501472Claude Sonnet 4.6
LMArena Text: non-English14251440Claude Sonnet 4.6
LMArena Text: Chinese14601491Claude Sonnet 4.6
LMArena Text: German14271428Claude Sonnet 4.6
LMArena Text: Japanese13901420Claude Sonnet 4.6
LMArena Text: Korean14021410Claude Sonnet 4.6
LMArena Text: French14591465Claude Sonnet 4.6
LMArena Text: Spanish14581464Claude Sonnet 4.6
LMArena Text: Russian14371440Claude Sonnet 4.6
LMArena Text: Polish14231443Claude Sonnet 4.6
LMArena Text: multi-turn14651464Claude Sonnet 4.5
LMArena Text: longer queries14751479Claude Sonnet 4.6
LMArena Text: writing and language14421444Claude Sonnet 4.6
LMArena Text: entertainment and media14281431Claude Sonnet 4.6
LMArena Vision: EnglishNot measured1298Only Claude Sonnet 4.6 measured
LMArena Vision: ChineseNot measured1307Only Claude Sonnet 4.6 measured
LMArena Vision: reading textNot measured1296Only Claude Sonnet 4.6 measured
LMArena Vision: humorNot measured1248Only Claude Sonnet 4.6 measured
LMArena Vision: recognizing thingsNot measured1195Only Claude Sonnet 4.6 measured
LMArena Vision: creative writingNot measured1272Only Claude Sonnet 4.6 measured
LMArena Document14501482Claude Sonnet 4.6
Neither model has a result on the other 11 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Sonnet 4.5 and Claude Sonnet 4.6
BenchmarkClaude Sonnet 4.5Claude 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 Sonnet 4.5$0.011Fits in one request
Claude Sonnet 4.6$0.011Fits in one request

Same cost

Repository review

50K input + 3K output tokens

Claude Sonnet 4.5$0.195Fits in one request
Claude Sonnet 4.6$0.195Fits in one request

Same cost

Agent loop

200K input + 10K output tokens

Claude Sonnet 4.5$0.750Fits in one request
Claude Sonnet 4.6$0.750Fits 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 Sonnet 4.5 and Claude Sonnet 4.6
SpecificationAnthropic Claude Sonnet 4.5Anthropic Claude Sonnet 4.6
MakerAnthropicAnthropic
WeightsNo public weights listedNo public weights listed
ReleasedSeptember 29, 2025February 17, 2026
Context window1M1M
Input $/Mtok$3.00$3.00
Output $/Mtok$15.00$15.00
Coding index59.157.8
Independent measurements behind it22
Cost per solved task$1.16$1.68
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Sonnet 4.5 better than Claude Sonnet 4.6 for coding?

Claude Sonnet 4.5 and Claude Sonnet 4.6 are level for coding, 59.1 against 57.8 on the Vibe Coding Index, so price and context decide. Pick Claude Sonnet 4.6 when what matters is LMArena WebDev or AA Coding Index, where it leads. Pick Claude Sonnet 4.5 when a solved task costs $1.16 against $1.68, or when what matters is Mystery game puzzles or MMLU Pro, where it leads.

Which is cheaper, Claude Sonnet 4.5 or Claude Sonnet 4.6?

Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; Claude Sonnet 4.6 costs $3.00 and $15.00. Per solved SWE-bench Verified task, Claude Sonnet 4.5 costs $1.16 and Claude Sonnet 4.6 $1.68.

Which has the bigger context window, Claude Sonnet 4.5 or Claude Sonnet 4.6?

Neither: both take 1M tokens.

How many benchmarks is the Claude Sonnet 4.5 vs Claude Sonnet 4.6 comparison based on?

76 benchmarks have a result for both models as of October 21, 2026. Claude Sonnet 4.5'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-sonnet-4-5-vs-claude-sonnet-4-6" title="Claude Sonnet 4.5 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-sonnet-4-5-vs-claude-sonnet-4-6">LLMBenchmark.ai, Claude Sonnet 4.5 vs Claude Sonnet 4.6</a></p>