Enter opens the highlighted result. Esc closes.

Claude Sonnet 4.5 vs DeepSeek V3.2

Claude Sonnet 4.5 leads DeepSeek V3.2 on coding, 39.5 to 30.0 on the Vibe Coding Index, and DeepSeek V3.2 costs 17.0x less per output token ($0.88 vs $15.00 per million). Updated October 22, 2026; 62 benchmarks have a result for both.

Replace Claude Sonnet 4.5 Replace DeepSeek V3.2
Claude Sonnet 4.5Anthropic
Coding
39.5
Overall
49.5
Output $/M
$15.00
59
DeepSeek V3.2DeepSeek
Coding
30.0
Overall
37.9
Output $/M
$0.88
3
vs boards won of 62 shared

Claude Sonnet 4.5 or DeepSeek V3.2: which to pick

Pick Claude Sonnet 4.5 for coding: it scores 39.5 on the Vibe Coding Index against 30.0 for DeepSeek V3.2.

Pick DeepSeek V3.2 for output tokens 17.0x cheaper ($0.88 vs $15.00 per million) and a lower cost per solved task ($0.99 against $1.16).

Model AClaude Sonnet 4.5Anthropic39.5/1003 independent benchmarks$1.16 per solved taskModel BDeepSeek V3.2DeepSeek30.0/1003 independent benchmarks$0.99 per solved task
Shared results
62
Claude Sonnet 4.5 only
33
DeepSeek V3.2 only
13
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 4.5 39.5 from 3 benchmarks, DeepSeek V3.2 30.0 from 3 benchmarks.
Widest category
Agentic work, 17.5 points apart on average over 1 shared benchmark.
Widest single gap
Vending-Bench 2: Claude Sonnet 4.5 $3,839 against DeepSeek V3.2 $1,034, 17.5 points apart on a 0 to 100 scale.
Output price
Claude Sonnet 4.5 $15.00 against DeepSeek V3.2 $0.88 per million output tokens, 17.0x apart.
Context window
Claude Sonnet 4.5 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 4.5BarsDeepSeek V3.2Ties
Coding111
Intelligence11
Agentic work10
Reasoning60
Math40
Knowledge100
Web design80
General181
All shared boards593
CodingLike-for-likeSix of these boards feed the Vibe Coding Index111
Coding benchmarks for Claude Sonnet 4.5 and DeepSeek V3.2
BenchmarkClaude Sonnet 4.5DeepSeek V3.2Leader
SWE-bench Verified74.8%70.0%Claude Sonnet 4.5
SWE-bench Multilingual67.0%59.0%Claude Sonnet 4.5
LMArena WebDev13941362Claude Sonnet 4.5
AA Coding Index52.144.2Claude Sonnet 4.5
LiveCodeBench (Vals AI)73.0%80.7%DeepSeek V3.2
SWE-bench Verified (Vals AI)70.0%67.6%Claude Sonnet 4.5
Vibe Code Bench (Vals AI)22.6%5.1%Claude Sonnet 4.5
LiveCodeBench (Artificial Analysis run)Not measured86.2%Only DeepSeek V3.2 measured
Terminal-Bench Hard (Artificial Analysis run)Not measured35.6%Only DeepSeek V3.2 measured
Terminal-Bench46.5%39.6%Claude Sonnet 4.5
GSO-Bench14.7%Not measuredOnly Claude Sonnet 4.5 measured
WeirdML47.7%Not measuredOnly Claude Sonnet 4.5 measured
Cybench60.0%Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text: coding14881453Claude Sonnet 4.5
LMArena Text: software and IT14731449Claude Sonnet 4.5
LMArena WebDev: React13861350Claude Sonnet 4.5
LMArena WebDev: HTML13991371Claude Sonnet 4.5
Neither model has a result on the other 22 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
Intelligence benchmarks for Claude Sonnet 4.5 and DeepSeek V3.2
BenchmarkClaude Sonnet 4.5DeepSeek V3.2Leader
AA Intelligence Index20.721.5DeepSeek V3.2
Epoch Capabilities Index146.7146.1Claude Sonnet 4.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
Agentic work benchmarks for Claude Sonnet 4.5 and DeepSeek V3.2
BenchmarkClaude Sonnet 4.5DeepSeek V3.2Leader
AA Agentic Index15.8Not measuredOnly Claude Sonnet 4.5 measured
Design Arena: agents building web apps1060Not measuredOnly Claude Sonnet 4.5 measured
Design Arena: agents building full-stack apps1050Not measuredOnly Claude Sonnet 4.5 measured
Design Arena: agents building mobile apps1137Not measuredOnly Claude Sonnet 4.5 measured
τ²-Bench TelecomNot measured90.6%Only DeepSeek V3.2 measured
APEX-AgentsNot measured21.3%Only DeepSeek V3.2 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
DeepResearch Bench52.6%Not measuredOnly Claude Sonnet 4.5 measured
OSWorld62.9%Not measuredOnly Claude Sonnet 4.5 measured
Vending-Bench 2$3,839$1,034Claude Sonnet 4.5
Berkeley Function Calling Leaderboard (BFCL)73.2%Not measuredOnly Claude Sonnet 4.5 measured
Neither model has a result on the other 28 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index60
Reasoning benchmarks for Claude Sonnet 4.5 and DeepSeek V3.2
BenchmarkClaude Sonnet 4.5DeepSeek V3.2Leader
GPQA Diamond81.6%80.3%Claude Sonnet 4.5
MMMU Pro (Vals AI)79.3%Not measuredOnly Claude Sonnet 4.5 measured
GPQA Diamond (Artificial Analysis run)Not measured84.0%Only DeepSeek V3.2 measured
Humanity's Last Exam (Artificial Analysis run)Not measured24.6%Only DeepSeek V3.2 measured
GPQA Diamond (Epoch AI run)82.3%Not measuredOnly Claude Sonnet 4.5 measured
ARC-AGI63.7%57.0%Claude Sonnet 4.5
ARC-AGI-213.6%4.0%Claude Sonnet 4.5
SimpleBench54.3%Not measuredOnly Claude Sonnet 4.5 measured
Chess puzzles10.0%Not measuredOnly Claude Sonnet 4.5 measured
Mystery game puzzles17.0%Not measuredOnly Claude Sonnet 4.5 measured
EBR-bench2.4%Not measuredOnly Claude Sonnet 4.5 measured
VPCT39.8%Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text: hard prompts14621434Claude Sonnet 4.5
LMArena Text: expert14831436Claude Sonnet 4.5
LMArena Text: hard prompts in English14711446Claude Sonnet 4.5
Kagi LLM Benchmark57.9%Not measuredOnly Claude Sonnet 4.5 measured
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index40
Math benchmarks for Claude Sonnet 4.5 and DeepSeek V3.2
BenchmarkClaude Sonnet 4.5DeepSeek V3.2Leader
AIME88.2%84.6%Claude Sonnet 4.5
MGSM (Vals AI)94.3%86.0%Claude Sonnet 4.5
AA Math IndexNot measured92.0Only DeepSeek V3.2 measured
AIME 2025 (Artificial Analysis run)Not measured92.0%Only DeepSeek V3.2 measured
OTIS Mock AIME77.8%Not measuredOnly Claude Sonnet 4.5 measured
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%Not measuredOnly Claude Sonnet 4.5 measured
MATH level 597.7%Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text: math14491435Claude Sonnet 4.5
LMArena Text: mathematical work14621440Claude Sonnet 4.5
Neither model has a result on the other 2 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index100
Knowledge benchmarks for Claude Sonnet 4.5 and DeepSeek V3.2
BenchmarkClaude Sonnet 4.5DeepSeek V3.2Leader
MMLU Pro87.4%84.9%Claude Sonnet 4.5
LegalBench (Vals AI)84.1%76.1%Claude Sonnet 4.5
CaseLaw (Vals AI)62.2%55.4%Claude Sonnet 4.5
CorpFin (Vals AI)62.0%51.0%Claude Sonnet 4.5
TaxEval (Vals AI)73.3%68.2%Claude Sonnet 4.5
MortgageTax (Vals AI)64.0%Not measuredOnly Claude Sonnet 4.5 measured
MedQA (Vals AI)94.7%93.9%Claude Sonnet 4.5
MedCode (Vals AI)44.1%Not measuredOnly Claude Sonnet 4.5 measured
MMLU Pro (Artificial Analysis run)Not measured86.2%Only DeepSeek V3.2 measured
SimpleQA Verified30.7%Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text: science14481446Claude Sonnet 4.5
LMArena Text: medicine and healthcare14441440Claude Sonnet 4.5
LMArena Text: legal and government14511425Claude Sonnet 4.5
LMArena Text: business and finance14401410Claude Sonnet 4.5
FACTS Benchmark Suite40.6%Not measuredOnly Claude Sonnet 4.5 measured
Neither model has a result on the other 3 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for Claude Sonnet 4.5 and DeepSeek V3.2
BenchmarkClaude Sonnet 4.5DeepSeek V3.2Leader
Design Arena: websites11891175Claude Sonnet 4.5
Design Arena: UI components11701146Claude Sonnet 4.5
Design Arena: game dev11661131Claude Sonnet 4.5
Design Arena: data viz11671158Claude Sonnet 4.5
Design Arena: 3D11571132Claude Sonnet 4.5
Design Arena: all code categories11821163Claude Sonnet 4.5
Design Arena: SVG11151032Claude Sonnet 4.5
Design Arena: ASCII art12051083Claude Sonnet 4.5
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index181
General benchmarks for Claude Sonnet 4.5 and DeepSeek V3.2
BenchmarkClaude Sonnet 4.5DeepSeek V3.2Leader
SAGE (Vals AI)36.1%Not measuredOnly Claude Sonnet 4.5 measured
MedScribe (Vals AI)84.5%Not measuredOnly Claude Sonnet 4.5 measured
IFBenchNot measured60.7%Only DeepSeek V3.2 measured
Long context reasoning (AA-LCR)Not measured73.3%Only DeepSeek V3.2 measured
DTBench83.2%85.6%DeepSeek V3.2
LMCA38.8%28.8%Claude Sonnet 4.5
CL-benchNot measured12.4%Only DeepSeek V3.2 measured
CL-bench LifeNot measured7.4%Only DeepSeek V3.2 measured
LMArena Text14381425Claude Sonnet 4.5
LMArena Text: instruction following14591413Claude Sonnet 4.5
LMArena Text: creative writing14421400Claude Sonnet 4.5
LMArena Text: English14501439Claude Sonnet 4.5
LMArena Text: non-English14251409Claude Sonnet 4.5
LMArena Text: Chinese14601455Claude Sonnet 4.5
LMArena Text: German14271413Claude Sonnet 4.5
LMArena Text: Japanese13901374Claude Sonnet 4.5
LMArena Text: Korean14021370Claude Sonnet 4.5
LMArena Text: French14591429Claude Sonnet 4.5
LMArena Text: Spanish14581424Claude Sonnet 4.5
LMArena Text: Russian14371424Claude Sonnet 4.5
LMArena Text: Polish14231419Claude Sonnet 4.5
LMArena Text: multi-turn14651427Claude Sonnet 4.5
LMArena Text: longer queries14751428Claude Sonnet 4.5
LMArena Text: writing and language14421407Claude Sonnet 4.5
LMArena Text: entertainment and media14281395Claude Sonnet 4.5
LMArena Document1450Not measuredOnly Claude Sonnet 4.5 measured
Neither model has a result on the other 20 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 DeepSeek V3.2
BenchmarkClaude Sonnet 4.5DeepSeek 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 4.5$0.011Fits 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 4.5$0.195Fits 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 4.5$0.750Fits 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 4.5 and DeepSeek V3.2
SpecificationAnthropic Claude Sonnet 4.5DeepSeek V3.2
MakerAnthropicDeepSeek
WeightsNo public weights listedOpen weights
ReleasedSeptember 29, 2025December 1, 2025
Context window1M164K
Input $/Mtok$3.00$0.29
Output $/Mtok$15.00$0.88
Coding index39.530.0
Independent measurements behind it33
Cost per solved task$1.16$0.99
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Sonnet 4.5 better than DeepSeek V3.2 for coding?

Pick Claude Sonnet 4.5 for coding: it scores 39.5 on the Vibe Coding Index against 30.0 for DeepSeek V3.2. Pick DeepSeek V3.2 for output tokens 17.0x cheaper ($0.88 vs $15.00 per million) and a lower cost per solved task ($0.99 against $1.16).

Which is cheaper, Claude Sonnet 4.5 or DeepSeek V3.2?

Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; DeepSeek V3.2 costs $0.29 and $0.88. Per solved SWE-bench Verified task, Claude Sonnet 4.5 costs $1.16 and DeepSeek V3.2 $0.99.

Which has the bigger context window, Claude Sonnet 4.5 or DeepSeek V3.2?

Claude Sonnet 4.5, with 1M tokens against 164K.

How many benchmarks is the Claude Sonnet 4.5 vs DeepSeek V3.2 comparison based on?

62 benchmarks have a result for both models as of October 22, 2026. Claude Sonnet 4.5's coding index rests on 3 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-4-5-vs-deepseek-v3-2" title="Claude Sonnet 4.5 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-4-5-vs-deepseek-v3-2">LLMBenchmark.ai, Claude Sonnet 4.5 vs DeepSeek V3.2</a></p>