Enter opens the highlighted result. Esc closes.

Claude Sonnet 5 vs DeepSeek V3.2

Claude Sonnet 5 leads DeepSeek V3.2 on coding, 57.7 to 30.0 on the Vibe Coding Index, and DeepSeek V3.2 costs 11.4x less per output token ($0.88 vs $10.00 per million). Updated October 22, 2026; 57 benchmarks have a result for both.

Replace Claude Sonnet 5 Replace DeepSeek V3.2
Claude Sonnet 5Anthropic
Coding
57.7
Overall
63.2
Output $/M
$10.00
57
DeepSeek V3.2DeepSeek
Coding
30.0
Overall
37.9
Output $/M
$0.88
0
vs boards won of 57 shared

Claude Sonnet 5 or DeepSeek V3.2: which to pick

Pick Claude Sonnet 5 for coding: it scores 57.7 on the Vibe Coding Index against 30.0 for DeepSeek V3.2.

Pick DeepSeek V3.2 for output tokens 11.4x cheaper ($0.88 vs $10.00 per million) and a lower cost per solved task ($0.99 against $1.87).

Model AClaude Sonnet 5Anthropic57.7/1006 independent benchmarks$1.87 per solved taskModel BDeepSeek V3.2DeepSeek30.0/1003 independent benchmarks$0.99 per solved task
Shared results
57
Claude Sonnet 5 only
64
DeepSeek V3.2 only
18
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 Sonnet 5 57.7 from 6 benchmarks, DeepSeek V3.2 30.0 from 3 benchmarks.
Widest category
Agentic work, 33.3 points apart on average over 2 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): Claude Sonnet 5 81.3% against DeepSeek V3.2 5.1%, 76.2 points apart on a 0 to 100 scale.
Output price
Claude Sonnet 5 $10.00 against DeepSeek V3.2 $0.88 per million output tokens, 11.4x apart.
Context window
Claude Sonnet 5 takes 1M tokens, DeepSeek V3.2 164K.

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 5BarsDeepSeek V3.2Ties
Coding90
Intelligence20
Agentic work20
Reasoning60
Math20
Knowledge80
Web design80
General200
All shared boards570
CodingLike-for-likeSix of these boards feed the Vibe Coding Index90
Coding benchmarks for Claude Sonnet 5 and DeepSeek V3.2
BenchmarkClaude Sonnet 5DeepSeek V3.2Leader
SWE-bench VerifiedNot measured70.0%Only DeepSeek V3.2 measured
SWE-bench MultilingualNot measured59.0%Only DeepSeek V3.2 measured
LiveBench coding74.7%Not measuredOnly Claude Sonnet 5 measured
LMArena WebDev15401362Claude Sonnet 5
AA Coding Index71.544.2Claude Sonnet 5
LiveCodeBench (Vals AI)82.4%80.7%Claude Sonnet 5
SWE-bench Verified (Vals AI)79.6%67.6%Claude Sonnet 5
Terminal-Bench 4 (Vals AI)10.6%Not measuredOnly Claude Sonnet 5 measured
Vibe Code Bench (Vals AI)81.3%5.1%Claude Sonnet 5
Code migration (Vals AI)44.4%Not measuredOnly Claude Sonnet 5 measured
ProgramBench (Vals AI)0.0%Not measuredOnly Claude Sonnet 5 measured
IOI (Vals AI)45.0%Not measuredOnly Claude Sonnet 5 measured
Terminal-Bench 2.1 (Vals AI)74.5%Not measuredOnly Claude Sonnet 5 measured
Vibe Code Bench 1-100 (Vals AI)13.8%Not measuredOnly Claude Sonnet 5 measured
SkillsBench (Vals AI)46.5%Not measuredOnly Claude Sonnet 5 measured
CyberBench (Vals AI)70.3%Not measuredOnly Claude Sonnet 5 measured
LiveCodeBench (Artificial Analysis run)Not measured86.2%Only DeepSeek V3.2 measured
SciCode54.3%Not measuredOnly Claude Sonnet 5 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured35.6%Only DeepSeek V3.2 measured
Terminal-BenchNot measured39.6%Only DeepSeek V3.2 measured
FrontierCode42.7%Not measuredOnly Claude Sonnet 5 measured
GSO-Bench37.3%Not measuredOnly Claude Sonnet 5 measured
WeirdML68.8%Not measuredOnly Claude Sonnet 5 measured
ALE-Bench1463.1Not measuredOnly Claude Sonnet 5 measured
LMArena Text: coding14831453Claude Sonnet 5
LMArena Text: software and IT14741449Claude Sonnet 5
LMArena WebDev: React15411350Claude Sonnet 5
LMArena WebDev: HTML15271371Claude Sonnet 5
LMArena WebDev: from an image1540Not measuredOnly Claude Sonnet 5 measured
SciCode10.7%Not measuredOnly Claude Sonnet 5 measured
Neither model has a result on the other 9 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Sonnet 5 and DeepSeek V3.2
BenchmarkClaude Sonnet 5DeepSeek V3.2Leader
AA Intelligence Index38.221.5Claude Sonnet 5
Epoch Capabilities Index156.9146.1Claude Sonnet 5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
Agentic work benchmarks for Claude Sonnet 5 and DeepSeek V3.2
BenchmarkClaude Sonnet 5DeepSeek V3.2Leader
AA Agentic Index43.6Not measuredOnly Claude Sonnet 5 measured
Design Arena: agents building web apps1245Not measuredOnly Claude Sonnet 5 measured
Design Arena: agents building full-stack apps1249Not measuredOnly Claude Sonnet 5 measured
Design Arena: agents building mobile apps1215Not measuredOnly Claude Sonnet 5 measured
Design Arena: agents building Android apps1227Not measuredOnly Claude Sonnet 5 measured
Design Arena: agents building Godot games1225Not measuredOnly Claude Sonnet 5 measured
Design Arena: agents building games1227Not measuredOnly Claude Sonnet 5 measured
Design Arena: HTML slides1168Not measuredOnly Claude Sonnet 5 measured
Design Arena: PowerPoint slides1191Not measuredOnly Claude Sonnet 5 measured
Design Arena: spreadsheets1035Not measuredOnly Claude Sonnet 5 measured
LiveBench research82.8%Not measuredOnly Claude Sonnet 5 measured
LiveBench browser72.0%Not measuredOnly Claude Sonnet 5 measured
LiveBench long agentic39.0%Not measuredOnly Claude Sonnet 5 measured
SREBench (Vals AI)0.4%Not measuredOnly Claude Sonnet 5 measured
Finance Agent (Vals AI)53.9%Not measuredOnly Claude Sonnet 5 measured
Tax Agent Bench (Vals AI)29.4%Not measuredOnly Claude Sonnet 5 measured
Legal Research Bench (Vals AI)41.8%Not measuredOnly Claude Sonnet 5 measured
Excel Modeling Benchmark (Vals AI)66.3%Not measuredOnly Claude Sonnet 5 measured
Terminal-Bench-Science (Vals AI)5.7%Not measuredOnly Claude Sonnet 5 measured
τ²-Bench TelecomNot measured90.6%Only DeepSeek V3.2 measured
APEX-Agents54.5%21.3%Claude Sonnet 5
Vending-Bench 2$6,378$1,034Claude Sonnet 5
Neither model has a result on the other 19 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index60
Reasoning benchmarks for Claude Sonnet 5 and DeepSeek V3.2
BenchmarkClaude Sonnet 5DeepSeek V3.2Leader
GPQA Diamond88.9%80.3%Claude Sonnet 5
LiveBench reasoning88.7%Not measuredOnly Claude Sonnet 5 measured
MMMU Pro (Vals AI)83.0%Not measuredOnly Claude Sonnet 5 measured
GPQA Diamond (Artificial Analysis run)91.1%84.0%Claude Sonnet 5
Humanity's Last Exam (Artificial Analysis run)41.3%24.6%Claude Sonnet 5
GPQA Diamond (Epoch AI run)90.5%Not measuredOnly Claude Sonnet 5 measured
ARC-AGINot measured57.0%Only DeepSeek V3.2 measured
ARC-AGI-2Not measured4.0%Only DeepSeek V3.2 measured
SimpleBench60.6%Not measuredOnly Claude Sonnet 5 measured
Chess puzzles45.0%Not measuredOnly Claude Sonnet 5 measured
Mystery game puzzles35.0%Not measuredOnly Claude Sonnet 5 measured
LMArena Text: hard prompts14611434Claude Sonnet 5
LMArena Text: expert14891436Claude Sonnet 5
LMArena Text: hard prompts in English14641446Claude Sonnet 5
LMArena Vision: diagrams1293Not measuredOnly Claude Sonnet 5 measured
LMArena Vision: homework1311Not measuredOnly Claude Sonnet 5 measured
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index20
Math benchmarks for Claude Sonnet 5 and DeepSeek V3.2
BenchmarkClaude Sonnet 5DeepSeek V3.2Leader
AIMENot measured84.6%Only DeepSeek V3.2 measured
MGSM (Vals AI)Not measured86.0%Only DeepSeek V3.2 measured
AA Math IndexNot measured92.0Only DeepSeek V3.2 measured
AIME 2025 (Artificial Analysis run)Not measured92.0%Only DeepSeek V3.2 measured
OTIS Mock AIME94.7%Not measuredOnly Claude Sonnet 5 measured
FrontierMath, tiers 1 to 365.6%Not measuredOnly Claude Sonnet 5 measured
FrontierMath, tier 429.3%Not measuredOnly Claude Sonnet 5 measured
ProofBench77.0%Not measuredOnly Claude Sonnet 5 measured
LMArena Text: math14671435Claude Sonnet 5
LMArena Text: mathematical work14811440Claude Sonnet 5
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index80
Knowledge benchmarks for Claude Sonnet 5 and DeepSeek V3.2
BenchmarkClaude Sonnet 5DeepSeek V3.2Leader
MMLU Pro87.5%84.9%Claude Sonnet 5
LegalBench (Vals AI)83.9%76.1%Claude Sonnet 5
CaseLaw (Vals AI)Not measured55.4%Only DeepSeek V3.2 measured
CorpFin (Vals AI)67.0%51.0%Claude Sonnet 5
TaxEval (Vals AI)75.6%68.2%Claude Sonnet 5
MortgageTax (Vals AI)70.0%Not measuredOnly Claude Sonnet 5 measured
MedQA (Vals AI)Not measured93.9%Only DeepSeek V3.2 measured
MedCode (Vals AI)47.5%Not measuredOnly Claude Sonnet 5 measured
MMLU Pro (Artificial Analysis run)Not measured86.2%Only DeepSeek V3.2 measured
SimpleQA Verified33.7%Not measuredOnly Claude Sonnet 5 measured
LMArena Text: science14601446Claude Sonnet 5
LMArena Text: medicine and healthcare14421440Claude Sonnet 5
LMArena Text: legal and government14541425Claude Sonnet 5
LMArena Text: business and finance14361410Claude Sonnet 5
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for Claude Sonnet 5 and DeepSeek V3.2
BenchmarkClaude Sonnet 5DeepSeek V3.2Leader
Design Arena: websites12741175Claude Sonnet 5
Design Arena: UI components12771146Claude Sonnet 5
Design Arena: game dev12771131Claude Sonnet 5
Design Arena: data viz12511158Claude Sonnet 5
Design Arena: 3D12611132Claude Sonnet 5
Design Arena: all code categories12751163Claude Sonnet 5
Design Arena: SVG11921032Claude Sonnet 5
Design Arena: ASCII art12071083Claude Sonnet 5
LiveBench design82.0%Not measuredOnly Claude Sonnet 5 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index200
General benchmarks for Claude Sonnet 5 and DeepSeek V3.2
BenchmarkClaude Sonnet 5DeepSeek V3.2Leader
LiveBench data analysis71.7%Not measuredOnly Claude Sonnet 5 measured
Public Benefits Bench (Vals AI)66.0%Not measuredOnly Claude Sonnet 5 measured
SAGE (Vals AI)48.9%Not measuredOnly Claude Sonnet 5 measured
MedScribe (Vals AI)76.0%Not measuredOnly Claude Sonnet 5 measured
Vals Multimodal Index68.8%Not measuredOnly Claude Sonnet 5 measured
IFBenchNot measured60.7%Only DeepSeek V3.2 measured
Long context reasoning (AA-LCR)82.0%73.3%Claude Sonnet 5
DTBench92.5%85.6%Claude Sonnet 5
LMCA50.0%28.8%Claude Sonnet 5
CL-benchNot measured12.4%Only DeepSeek V3.2 measured
Surface Evolver Bench60.0%Not measuredOnly Claude Sonnet 5 measured
CL-bench LifeNot measured7.4%Only DeepSeek V3.2 measured
LMArena Text14421425Claude Sonnet 5
LMArena Text: instruction following14521413Claude Sonnet 5
LMArena Text: creative writing14161400Claude Sonnet 5
LMArena Vision1273Not measuredOnly Claude Sonnet 5 measured
LMArena Text: English14501439Claude Sonnet 5
LMArena Text: non-English14311409Claude Sonnet 5
LMArena Text: Chinese14781455Claude Sonnet 5
LMArena Text: German14421413Claude Sonnet 5
LMArena Text: Japanese14221374Claude Sonnet 5
LMArena Text: Korean14121370Claude Sonnet 5
LMArena Text: French14631429Claude Sonnet 5
LMArena Text: Spanish14381424Claude Sonnet 5
LMArena Text: Russian14501424Claude Sonnet 5
LMArena Text: Polish14251419Claude Sonnet 5
LMArena Text: multi-turn14531427Claude Sonnet 5
LMArena Text: longer queries14621428Claude Sonnet 5
LMArena Text: writing and language14361407Claude Sonnet 5
LMArena Text: entertainment and media14111395Claude Sonnet 5
LMArena Vision: English1275Not measuredOnly Claude Sonnet 5 measured
LMArena Vision: Chinese1331Not measuredOnly Claude Sonnet 5 measured
LMArena Vision: reading text1288Not measuredOnly Claude Sonnet 5 measured
LMArena Vision: humor1261Not measuredOnly Claude Sonnet 5 measured
LMArena Vision: creative writing1246Not measuredOnly Claude Sonnet 5 measured
LMArena Document1466Not measuredOnly Claude Sonnet 5 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 Sonnet 5 and DeepSeek V3.2
BenchmarkClaude Sonnet 5DeepSeek V3.2Leader
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 5$0.0070Fits in one request
DeepSeek V3.2$0.0007Fits in one request

DeepSeek V3.2 costs less

Repository review

50K input + 3K output tokens

Claude Sonnet 5$0.130Fits in one request
DeepSeek V3.2$0.017Fits in one request

DeepSeek V3.2 costs less

Agent loop

200K input + 10K output tokens

Claude Sonnet 5$0.500Fits in one request
DeepSeek V3.2$0.067Exceeds the context window

DeepSeek V3.2 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 Sonnet 5 and DeepSeek V3.2
SpecificationAnthropic Claude Sonnet 5DeepSeek V3.2
MakerAnthropicDeepSeek
WeightsNo public weights listedOpen weights
ReleasedJune 30, 2026December 1, 2025
Context window1M164K
Input $/Mtok$2.00$0.29
Output $/Mtok$10.00$0.88
Coding index57.730.0
Independent measurements behind it63
Cost per solved task$1.87$0.99
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Sonnet 5 better than DeepSeek V3.2 for coding?

Pick Claude Sonnet 5 for coding: it scores 57.7 on the Vibe Coding Index against 30.0 for DeepSeek V3.2. Pick DeepSeek V3.2 for output tokens 11.4x cheaper ($0.88 vs $10.00 per million) and a lower cost per solved task ($0.99 against $1.87).

Which is cheaper, Claude Sonnet 5 or DeepSeek V3.2?

Claude Sonnet 5 costs $2.00 per million input tokens and $10.00 per million output tokens; DeepSeek V3.2 costs $0.29 and $0.88. Per solved SWE-bench Verified task, Claude Sonnet 5 costs $1.87 and DeepSeek V3.2 $0.99.

Which has the bigger context window, Claude Sonnet 5 or DeepSeek V3.2?

Claude Sonnet 5, with 1M tokens against 164K.

How many benchmarks is the Claude Sonnet 5 vs DeepSeek V3.2 comparison based on?

57 benchmarks have a result for both models as of October 22, 2026. Claude Sonnet 5's coding index rests on 6 independent benchmarks and DeepSeek V3.2's on 3. 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-5-vs-deepseek-v3-2" title="Claude Sonnet 5 vs DeepSeek V3.2, 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-5-vs-deepseek-v3-2">LLMBenchmark.ai, Claude Sonnet 5 vs DeepSeek V3.2</a></p>