Enter opens the highlighted result. Esc closes.

Claude Sonnet 5 vs DeepSeek V4 Pro 0423

Claude Sonnet 5 leads DeepSeek V4 Pro 0423 on coding, 57.7 to 38.7 on the Vibe Coding Index, and DeepSeek V4 Pro 0423 costs 3.4x less per output token ($2.976 vs $10.00 per million). Updated October 22, 2026; 81 benchmarks have a result for both.

Replace Claude Sonnet 5 Replace DeepSeek V4 Pro 0423
Claude Sonnet 5Anthropic
Coding
57.7
Overall
63.2
Output $/M
$10.00
53
DeepSeek V4 Pro 0423DeepSeek
Coding
38.7
Overall
50.0
Output $/M
$2.976
27
vs boards won of 81 shared, 1 tied

Claude Sonnet 5 or DeepSeek V4 Pro 0423: which to pick

Pick Claude Sonnet 5 for coding: it scores 57.7 on the Vibe Coding Index against 38.7 for DeepSeek V4 Pro 0423.

Pick DeepSeek V4 Pro 0423 for output tokens 3.4x cheaper ($2.976 vs $10.00 per million) and a lower cost per solved task ($0.57 against $1.87).

Model AClaude Sonnet 5Anthropic57.7/1006 independent benchmarks$1.87 per solved taskModel BDeepSeek V4 Pro 0423DeepSeek38.7/1005 independent benchmarks$0.57 per solved task
Shared results
81
Claude Sonnet 5 only
40
DeepSeek V4 Pro 0423 only
3
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 V4 Pro 0423 38.7 from 5 benchmarks.
Widest category
Math, 19.7 points apart on average over 6 shared benchmarks.
Widest single gap
ProofBench: Claude Sonnet 5 77.0% against DeepSeek V4 Pro 0423 16.0%, 61.0 points apart on a 0 to 100 scale.
Output price
Claude Sonnet 5 $10.00 against DeepSeek V4 Pro 0423 $2.976 per million output tokens, 3.4x apart.
Context window
Claude Sonnet 5 takes 1M tokens, DeepSeek V4 Pro 0423 1.05M.

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 V4 Pro 0423Ties
Coding1331 tie
Intelligence20
Agentic work90
Reasoning34
Math51
Knowledge55
Web design80
General814
All shared boards53271 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index133
Coding benchmarks for Claude Sonnet 5 and DeepSeek V4 Pro 0423
BenchmarkClaude Sonnet 5DeepSeek V4 Pro 0423Leader
LiveBench coding74.7%Not measuredOnly Claude Sonnet 5 measured
LMArena WebDev15401447Claude Sonnet 5
AA Coding Index71.559.4Claude Sonnet 5
LiveCodeBench (Vals AI)82.4%87.5%DeepSeek V4 Pro 0423
SWE-bench Verified (Vals AI)79.6%77.4%Claude Sonnet 5
Terminal-Bench 4 (Vals AI)10.6%11.1%DeepSeek V4 Pro 0423
Vibe Code Bench (Vals AI)81.3%49.9%Claude Sonnet 5
Code migration (Vals AI)44.4%26.2%Claude Sonnet 5
ProgramBench (Vals AI)0.0%0.0%Tie
IOI (Vals AI)45.0%Not measuredOnly Claude Sonnet 5 measured
Terminal-Bench 2.1 (Vals AI)74.5%50.2%Claude Sonnet 5
Vibe Code Bench 1-100 (Vals AI)13.8%Not measuredOnly Claude Sonnet 5 measured
SkillsBench (Vals AI)46.5%51.3%DeepSeek V4 Pro 0423
CyberBench (Vals AI)70.3%Not measuredOnly Claude Sonnet 5 measured
SciCode54.3%Not measuredOnly Claude Sonnet 5 measured
FrontierCode42.7%17.6%Claude Sonnet 5
GSO-Bench37.3%Not measuredOnly Claude Sonnet 5 measured
WeirdML68.8%48.9%Claude Sonnet 5
ALE-Bench1463.11006.1Claude Sonnet 5
LMArena Text: coding14831470Claude Sonnet 5
LMArena Text: software and IT14741469Claude Sonnet 5
LMArena WebDev: React15411441Claude Sonnet 5
LMArena WebDev: HTML15271435Claude 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 14 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Sonnet 5 and DeepSeek V4 Pro 0423
BenchmarkClaude Sonnet 5DeepSeek V4 Pro 0423Leader
AA Intelligence Index38.230.4Claude Sonnet 5
Epoch Capabilities Index156.9149.1Claude Sonnet 5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index90
Agentic work benchmarks for Claude Sonnet 5 and DeepSeek V4 Pro 0423
BenchmarkClaude Sonnet 5DeepSeek V4 Pro 0423Leader
AA Agentic Index43.626.3Claude Sonnet 5
Design Arena: agents building web apps12451000Claude Sonnet 5
Design Arena: agents building full-stack apps1249948Claude Sonnet 5
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 games12251059Claude Sonnet 5
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%44.1%Claude Sonnet 5
Tax Agent Bench (Vals AI)29.4%25.2%Claude Sonnet 5
Legal Research Bench (Vals AI)41.8%23.1%Claude Sonnet 5
Excel Modeling Benchmark (Vals AI)66.3%51.6%Claude Sonnet 5
Terminal-Bench-Science (Vals AI)5.7%Not measuredOnly Claude Sonnet 5 measured
APEX-Agents54.5%Not measuredOnly Claude Sonnet 5 measured
Vending-Bench 2$6,378$3,285Claude Sonnet 5
Neither model has a result on the other 20 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index34
Reasoning benchmarks for Claude Sonnet 5 and DeepSeek V4 Pro 0423
BenchmarkClaude Sonnet 5DeepSeek V4 Pro 0423Leader
GPQA Diamond88.9%89.4%DeepSeek V4 Pro 0423
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%Not measuredOnly Claude Sonnet 5 measured
Humanity's Last Exam (Artificial Analysis run)41.3%Not measuredOnly Claude Sonnet 5 measured
GPQA Diamond (Epoch AI run)90.5%90.9%DeepSeek V4 Pro 0423
SimpleBench60.6%Not measuredOnly Claude Sonnet 5 measured
Chess puzzles45.0%19.0%Claude Sonnet 5
Mystery game puzzles35.0%17.0%Claude Sonnet 5
LMArena Text: hard prompts14611461DeepSeek V4 Pro 0423
LMArena Text: expert14891463Claude Sonnet 5
LMArena Text: hard prompts in English14641466DeepSeek V4 Pro 0423
LMArena Vision: diagrams1293Not measuredOnly Claude Sonnet 5 measured
LMArena Vision: homework1311Not measuredOnly Claude Sonnet 5 measured
Kagi LLM BenchmarkNot measured53.5%Only DeepSeek V4 Pro 0423 measured
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index51
Math benchmarks for Claude Sonnet 5 and DeepSeek V4 Pro 0423
BenchmarkClaude Sonnet 5DeepSeek V4 Pro 0423Leader
OTIS Mock AIME94.7%96.7%DeepSeek V4 Pro 0423
FrontierMath, tiers 1 to 365.6%45.3%Claude Sonnet 5
FrontierMath, tier 429.3%2.4%Claude Sonnet 5
ProofBench77.0%16.0%Claude Sonnet 5
LMArena Text: math14671443Claude Sonnet 5
LMArena Text: mathematical work14811455Claude Sonnet 5
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index55
Knowledge benchmarks for Claude Sonnet 5 and DeepSeek V4 Pro 0423
BenchmarkClaude Sonnet 5DeepSeek V4 Pro 0423Leader
MMLU Pro87.5%87.3%Claude Sonnet 5
LegalBench (Vals AI)83.9%80.3%Claude Sonnet 5
CaseLaw (Vals AI)Not measured59.4%Only DeepSeek V4 Pro 0423 measured
CorpFin (Vals AI)67.0%61.4%Claude Sonnet 5
TaxEval (Vals AI)75.6%72.1%Claude Sonnet 5
MortgageTax (Vals AI)70.0%Not measuredOnly Claude Sonnet 5 measured
MedCode (Vals AI)47.5%40.5%Claude Sonnet 5
SimpleQA Verified33.7%47.0%DeepSeek V4 Pro 0423
LMArena Text: science14601470DeepSeek V4 Pro 0423
LMArena Text: medicine and healthcare14421466DeepSeek V4 Pro 0423
LMArena Text: legal and government14541464DeepSeek V4 Pro 0423
LMArena Text: business and finance14361443DeepSeek V4 Pro 0423
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for Claude Sonnet 5 and DeepSeek V4 Pro 0423
BenchmarkClaude Sonnet 5DeepSeek V4 Pro 0423Leader
Design Arena: websites12741234Claude Sonnet 5
Design Arena: UI components12771219Claude Sonnet 5
Design Arena: game dev12771228Claude Sonnet 5
Design Arena: data viz12511203Claude Sonnet 5
Design Arena: 3D12611253Claude Sonnet 5
Design Arena: all code categories12751240Claude Sonnet 5
Design Arena: SVG11921139Claude Sonnet 5
Design Arena: ASCII art12071149Claude Sonnet 5
LiveBench design82.0%Not measuredOnly Claude Sonnet 5 measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index814
General benchmarks for Claude Sonnet 5 and DeepSeek V4 Pro 0423
BenchmarkClaude Sonnet 5DeepSeek V4 Pro 0423Leader
LiveBench data analysis71.7%Not measuredOnly Claude Sonnet 5 measured
Public Benefits Bench (Vals AI)66.0%62.9%Claude Sonnet 5
SAGE (Vals AI)48.9%Not measuredOnly Claude Sonnet 5 measured
MedScribe (Vals AI)76.0%75.1%Claude Sonnet 5
Vals Multimodal Index68.8%Not measuredOnly Claude Sonnet 5 measured
Long context reasoning (AA-LCR)82.0%Not measuredOnly Claude Sonnet 5 measured
DTBench92.5%90.7%Claude Sonnet 5
LMCA50.0%41.2%Claude Sonnet 5
Surface Evolver Bench60.0%40.0%Claude Sonnet 5
CL-bench LifeNot measured13.5%Only DeepSeek V4 Pro 0423 measured
LMArena Text14421451DeepSeek V4 Pro 0423
LMArena Text: instruction following14521445Claude Sonnet 5
LMArena Text: creative writing14161446DeepSeek V4 Pro 0423
LMArena Vision1273Not measuredOnly Claude Sonnet 5 measured
LMArena Text: English14501459DeepSeek V4 Pro 0423
LMArena Text: non-English14311439DeepSeek V4 Pro 0423
LMArena Text: Chinese14781481DeepSeek V4 Pro 0423
LMArena Text: German14421458DeepSeek V4 Pro 0423
LMArena Text: Japanese14221446DeepSeek V4 Pro 0423
LMArena Text: Korean14121409Claude Sonnet 5
LMArena Text: French14631473DeepSeek V4 Pro 0423
LMArena Text: Spanish14381457DeepSeek V4 Pro 0423
LMArena Text: Russian14501453DeepSeek V4 Pro 0423
LMArena Text: Polish14251461DeepSeek V4 Pro 0423
LMArena Text: multi-turn14531468DeepSeek V4 Pro 0423
LMArena Text: longer queries14621458Claude Sonnet 5
LMArena Text: writing and language14361447DeepSeek V4 Pro 0423
LMArena Text: entertainment and media14111431DeepSeek V4 Pro 0423
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 12 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 V4 Pro 0423
BenchmarkClaude Sonnet 5DeepSeek V4 Pro 0423Leader
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 V4 Pro 0423$0.0028Fits in one request

DeepSeek V4 Pro 0423 costs less

Repository review

50K input + 3K output tokens

Claude Sonnet 5$0.130Fits in one request
DeepSeek V4 Pro 0423$0.077Fits in one request

DeepSeek V4 Pro 0423 costs less

Agent loop

200K input + 10K output tokens

Claude Sonnet 5$0.500Fits in one request
DeepSeek V4 Pro 0423$0.301Fits in one request

DeepSeek V4 Pro 0423 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 V4 Pro 0423
SpecificationAnthropic Claude Sonnet 5DeepSeek V4 Pro 0423
MakerAnthropicDeepSeek
WeightsNo public weights listedOpen weights
ReleasedJune 30, 2026April 24, 2026
Context window1M1.05M
Input $/Mtok$2.00$1.358
Output $/Mtok$10.00$2.976
Coding index57.738.7
Independent measurements behind it65
Cost per solved task$1.87$0.57
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Sonnet 5 better than DeepSeek V4 Pro 0423 for coding?

Pick Claude Sonnet 5 for coding: it scores 57.7 on the Vibe Coding Index against 38.7 for DeepSeek V4 Pro 0423. Pick DeepSeek V4 Pro 0423 for output tokens 3.4x cheaper ($2.976 vs $10.00 per million) and a lower cost per solved task ($0.57 against $1.87).

Which is cheaper, Claude Sonnet 5 or DeepSeek V4 Pro 0423?

Claude Sonnet 5 costs $2.00 per million input tokens and $10.00 per million output tokens; DeepSeek V4 Pro 0423 costs $1.358 and $2.976. Per solved SWE-bench Verified task, Claude Sonnet 5 costs $1.87 and DeepSeek V4 Pro 0423 $0.57.

Which has the bigger context window, Claude Sonnet 5 or DeepSeek V4 Pro 0423?

DeepSeek V4 Pro 0423, with 1.05M tokens against 1M.

How many benchmarks is the Claude Sonnet 5 vs DeepSeek V4 Pro 0423 comparison based on?

81 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 V4 Pro 0423's on 5. 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-v4-pro" title="Claude Sonnet 5 vs DeepSeek V4 Pro 0423, 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-v4-pro">LLMBenchmark.ai, Claude Sonnet 5 vs DeepSeek V4 Pro 0423</a></p>