Enter opens the highlighted result. Esc closes.

Claude Sonnet 5.5 vs DeepSeek V4 Pro 0813

Updated October 21, 2026. 62 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Sonnet 5.5 Replace DeepSeek V4 Pro 0813
Claude Sonnet 5.5Anthropic
Coding
88.9
Overall
56.0
Output $/M
$10.00
59
DeepSeek V4 Pro 0813DeepSeek
Coding
54.6
Overall
36.0
Output $/M
$1.98
3
vs boards won of 62 shared

Decision reading

Pick Claude Sonnet 5.5 for coding: it scores 88.9 on the Vibe Coding Index against 54.6 for DeepSeek V4 Pro 0813.

Pick DeepSeek V4 Pro 0813 when output tokens cost 5.1x less, or when the context window is larger, 1.05M against 1M tokens.

Model AClaude Sonnet 5.5Anthropic88.9/1002 independent benchmarksNo cost per solved taskModel BDeepSeek V4 Pro 0813DeepSeek54.6/1001 independent benchmark$0.10 per solved task
Shared results
62
Claude Sonnet 5.5 only
33
DeepSeek V4 Pro 0813 only
16
Like-for-like categories
7 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 5.5 88.9 from 2 benchmarks, DeepSeek V4 Pro 0813 54.6 from 1 benchmark.
Widest category
Math, 25.0 points apart on average over 6 shared benchmarks.
Widest single gap
FrontierMath, tier 4: Claude Sonnet 5.5 80.5% against DeepSeek V4 Pro 0813 26.8%, 53.7 points apart on a 0 to 100 scale.
Output price
Claude Sonnet 5.5 $10.00 against DeepSeek V4 Pro 0813 $1.98 per million output tokens, 5.1x apart.
Context window
Claude Sonnet 5.5 takes 1M tokens, DeepSeek V4 Pro 0813 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 5.5BarsDeepSeek V4 Pro 0813Ties
Coding141
Intelligence20
Agentic work71
Reasoning70
Math60
Knowledge51
General180
All shared boards593
CodingLike-for-likeFour of these boards feed the Vibe Coding Index141
Coding benchmarks for Claude Sonnet 5.5 and DeepSeek V4 Pro 0813
BenchmarkClaude Sonnet 5.5DeepSeek V4 Pro 0813Leader
LiveBench coding94.7%Not measuredOnly Claude Sonnet 5.5 measured
LMArena WebDev17681582Claude Sonnet 5.5
AA Coding IndexNot measured68.8Only DeepSeek V4 Pro 0813 measured
LiveCodeBench (Vals AI)Not measured87.5%Only DeepSeek V4 Pro 0813 measured
SWE-bench Verified (Vals AI)Not measured96.4%Only DeepSeek V4 Pro 0813 measured
Terminal-Bench 4 (Vals AI)64.1%14.1%Claude Sonnet 5.5
Vibe Code Bench (Vals AI)92.4%82.3%Claude Sonnet 5.5
Code migration (Vals AI)69.8%41.5%Claude Sonnet 5.5
ProgramBench (Vals AI)6.5%0.0%Claude Sonnet 5.5
IOI (Vals AI)83.1%51.6%Claude Sonnet 5.5
Terminal-Bench 2.1 (Vals AI)83.2%54.7%Claude Sonnet 5.5
SWE-bench Multimodal (Vals AI)58.3%Not measuredOnly Claude Sonnet 5.5 measured
Vibe Code Bench 1-100 (Vals AI)Not measured17.5%Only DeepSeek V4 Pro 0813 measured
SkillsBench (Vals AI)Not measured53.8%Only DeepSeek V4 Pro 0813 measured
CyberBench (Vals AI)59.6%72.9%DeepSeek V4 Pro 0813
SciCode61.0%51.0%Claude Sonnet 5.5
FrontierCode52.1%28.5%Claude Sonnet 5.5
FrontierSWE61.9%Not measuredOnly Claude Sonnet 5.5 measured
WeirdMLNot measured66.2%Only DeepSeek V4 Pro 0813 measured
ALE-Bench1819.11403.2Claude Sonnet 5.5
LMArena Text: coding15131469Claude Sonnet 5.5
LMArena Text: software and IT15041462Claude Sonnet 5.5
LMArena WebDev: React18171588Claude Sonnet 5.5
LMArena WebDev: HTML17411566Claude Sonnet 5.5
LMArena WebDev: from an image1737Not measuredOnly Claude Sonnet 5.5 measured
Neither model has a result on the other 13 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Sonnet 5.5 and DeepSeek V4 Pro 0813
BenchmarkClaude Sonnet 5.5DeepSeek V4 Pro 0813Leader
AA Intelligence Index56.036.0Claude Sonnet 5.5
Epoch Capabilities Index166.2155.6Claude Sonnet 5.5
Agentic workLike-for-likePublic boards, shown as published, kept out of the index71
Agentic work benchmarks for Claude Sonnet 5.5 and DeepSeek V4 Pro 0813
BenchmarkClaude Sonnet 5.5DeepSeek V4 Pro 0813Leader
AA Agentic IndexNot measured41.3Only DeepSeek V4 Pro 0813 measured
Design Arena: agents building web apps1303Not measuredOnly Claude Sonnet 5.5 measured
Design Arena: agents building mobile apps1265Not measuredOnly Claude Sonnet 5.5 measured
Design Arena: spreadsheets1245Not measuredOnly Claude Sonnet 5.5 measured
LiveBench research83.6%Not measuredOnly Claude Sonnet 5.5 measured
LiveBench browser84.0%Not measuredOnly Claude Sonnet 5.5 measured
LiveBench long agentic78.8%Not measuredOnly Claude Sonnet 5.5 measured
SREBench (Vals AI)30.1%1.9%Claude Sonnet 5.5
Finance Agent (Vals AI)58.1%50.4%Claude Sonnet 5.5
Tax Agent Bench (Vals AI)42.0%26.8%Claude Sonnet 5.5
Legal Research Bench (Vals AI)48.1%40.9%Claude Sonnet 5.5
Harvey's Legal Agent Benchmark (Vals AI)10.4%10.8%DeepSeek V4 Pro 0813
Excel Modeling Benchmark (Vals AI)75.7%52.8%Claude Sonnet 5.5
BioMysteryBench (Vals AI)81.1%Not measuredOnly Claude Sonnet 5.5 measured
Terminal-Bench-Science (Vals AI)47.1%4.3%Claude Sonnet 5.5
Vals Science Index59.1%Not measuredOnly Claude Sonnet 5.5 measured
APEX-Agents75.5%47.3%Claude Sonnet 5.5
SpireClimb1.3%Not measuredOnly Claude Sonnet 5.5 measured
Vending-Bench 2$11,165Not measuredOnly Claude Sonnet 5.5 measured
Neither model has a result on the other 20 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index70
Reasoning benchmarks for Claude Sonnet 5.5 and DeepSeek V4 Pro 0813
BenchmarkClaude Sonnet 5.5DeepSeek V4 Pro 0813Leader
GPQA DiamondNot measured92.4%Only DeepSeek V4 Pro 0813 measured
LiveBench reasoning91.6%Not measuredOnly Claude Sonnet 5.5 measured
MysteryMechanism (Vals AI)49.1%Not measuredOnly Claude Sonnet 5.5 measured
GPQA Diamond (Artificial Analysis run)Not measured92.8%Only DeepSeek V4 Pro 0813 measured
Humanity's Last Exam (Artificial Analysis run)55.0%41.0%Claude Sonnet 5.5
GPQA Diamond (Epoch AI run)95.6%91.7%Claude Sonnet 5.5
ARC-AGINot measured90.5%Only DeepSeek V4 Pro 0813 measured
ARC-AGI-2Not measured61.3%Only DeepSeek V4 Pro 0813 measured
Chess puzzles59.0%46.0%Claude Sonnet 5.5
Mystery game puzzles65.0%43.0%Claude Sonnet 5.5
LMArena Text: hard prompts14941458Claude Sonnet 5.5
LMArena Text: expert15311459Claude Sonnet 5.5
LMArena Text: hard prompts in English15021463Claude Sonnet 5.5
LMArena Vision: diagrams1329Not measuredOnly Claude Sonnet 5.5 measured
LMArena Vision: homework1331Not measuredOnly Claude Sonnet 5.5 measured
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for Claude Sonnet 5.5 and DeepSeek V4 Pro 0813
BenchmarkClaude Sonnet 5.5DeepSeek V4 Pro 0813Leader
OTIS Mock AIME100.0%98.6%Claude Sonnet 5.5
FrontierMath, tiers 1 to 388.8%64.6%Claude Sonnet 5.5
FrontierMath, tier 480.5%26.8%Claude Sonnet 5.5
ProofBench100.0%50.0%Claude Sonnet 5.5
LMArena Text: math14971441Claude Sonnet 5.5
LMArena Text: mathematical work15101443Claude Sonnet 5.5
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index51
Knowledge benchmarks for Claude Sonnet 5.5 and DeepSeek V4 Pro 0813
BenchmarkClaude Sonnet 5.5DeepSeek V4 Pro 0813Leader
MMLU ProNot measured87.0%Only DeepSeek V4 Pro 0813 measured
LegalBench (Vals AI)Not measured82.4%Only DeepSeek V4 Pro 0813 measured
CorpFin (Vals AI)Not measured65.4%Only DeepSeek V4 Pro 0813 measured
TaxEval (Vals AI)Not measured73.1%Only DeepSeek V4 Pro 0813 measured
MedCode (Vals AI)52.9%42.5%Claude Sonnet 5.5
SimpleQA Verified46.5%52.9%DeepSeek V4 Pro 0813
LMArena Text: science14831457Claude Sonnet 5.5
LMArena Text: medicine and healthcare14641446Claude Sonnet 5.5
LMArena Text: legal and government14831459Claude Sonnet 5.5
LMArena Text: business and finance14681442Claude Sonnet 5.5
Neither model has a result on the other 7 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Web design benchmarks for Claude Sonnet 5.5 and DeepSeek V4 Pro 0813
BenchmarkClaude Sonnet 5.5DeepSeek V4 Pro 0813Leader
Design Arena: websites1326Not measuredOnly Claude Sonnet 5.5 measured
Design Arena: UI components1367Not measuredOnly Claude Sonnet 5.5 measured
Design Arena: game dev1469Not measuredOnly Claude Sonnet 5.5 measured
Design Arena: data viz1389Not measuredOnly Claude Sonnet 5.5 measured
Design Arena: 3D1458Not measuredOnly Claude Sonnet 5.5 measured
Design Arena: all code categories1364Not measuredOnly Claude Sonnet 5.5 measured
LiveBench design85.0%Not measuredOnly Claude Sonnet 5.5 measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index180
General benchmarks for Claude Sonnet 5.5 and DeepSeek V4 Pro 0813
BenchmarkClaude Sonnet 5.5DeepSeek V4 Pro 0813Leader
Vals Index70.8%53.0%Claude Sonnet 5.5
LiveBench data analysis59.5%Not measuredOnly Claude Sonnet 5.5 measured
Public Benefits Bench (Vals AI)67.2%Not measuredOnly Claude Sonnet 5.5 measured
SAGE (Vals AI)51.8%Not measuredOnly Claude Sonnet 5.5 measured
MedScribe (Vals AI)91.1%80.2%Claude Sonnet 5.5
Long context reasoning (AA-LCR)82.7%80.3%Claude Sonnet 5.5
DTBench97.3%93.9%Claude Sonnet 5.5
LMCA68.3%45.5%Claude Sonnet 5.5
Furniture assembly75.0%Not measuredOnly Claude Sonnet 5.5 measured
LMArena Text14731446Claude Sonnet 5.5
LMArena Text: instruction following14921448Claude Sonnet 5.5
LMArena Text: creative writing14671439Claude Sonnet 5.5
LMArena Vision1287Not measuredOnly Claude Sonnet 5.5 measured
LMArena Text: English14841457Claude Sonnet 5.5
LMArena Text: non-English14561431Claude Sonnet 5.5
LMArena Text: Chinese15351481Claude Sonnet 5.5
LMArena Text: KoreanNot measured1449Only DeepSeek V4 Pro 0813 measured
LMArena Text: French14991446Claude Sonnet 5.5
LMArena Text: Spanish14511435Claude Sonnet 5.5
LMArena Text: Russian14541448Claude Sonnet 5.5
LMArena Text: multi-turn14651454Claude Sonnet 5.5
LMArena Text: longer queries14951458Claude Sonnet 5.5
LMArena Text: writing and language14741443Claude Sonnet 5.5
LMArena Text: entertainment and media14611424Claude Sonnet 5.5
LMArena Vision: English1289Not measuredOnly Claude Sonnet 5.5 measured
LMArena Vision: reading text1297Not measuredOnly Claude Sonnet 5.5 measured
LMArena Vision: creative writing1242Not measuredOnly Claude Sonnet 5.5 measured
Neither model has a result on the other 19 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Sonnet 5.5 and DeepSeek V4 Pro 0813
BenchmarkClaude Sonnet 5.5DeepSeek V4 Pro 0813Leader
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 5.5$0.0070Fits in one request
DeepSeek V4 Pro 0813$0.0016Fits in one request

DeepSeek V4 Pro 0813 costs less

Repository review

50K input + 3K output tokens

Claude Sonnet 5.5$0.130Fits in one request
DeepSeek V4 Pro 0813$0.039Fits in one request

DeepSeek V4 Pro 0813 costs less

Agent loop

200K input + 10K output tokens

Claude Sonnet 5.5$0.500Fits in one request
DeepSeek V4 Pro 0813$0.152Fits in one request

DeepSeek V4 Pro 0813 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 5.5 and DeepSeek V4 Pro 0813
SpecificationAnthropic Claude Sonnet 5.5DeepSeek V4 Pro 0813
MakerAnthropicDeepSeek
WeightsNo public weights listedOpen weights
ReleasedSeptember 28, 2026August 12, 2026
Context window1M1.05M
Input $/Mtok$2.00$0.66
Output $/Mtok$10.00$1.98
Coding index88.954.6
Independent measurements behind it21
Cost per solved taskNot computable$0.10
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Sonnet 5.5 better than DeepSeek V4 Pro 0813 for coding?

Pick Claude Sonnet 5.5 for coding: it scores 88.9 on the Vibe Coding Index against 54.6 for DeepSeek V4 Pro 0813. Pick DeepSeek V4 Pro 0813 when output tokens cost 5.1x less, or when the context window is larger, 1.05M against 1M tokens.

Which is cheaper, Claude Sonnet 5.5 or DeepSeek V4 Pro 0813?

Claude Sonnet 5.5 costs $2.00 per million input tokens and $10.00 per million output tokens; DeepSeek V4 Pro 0813 costs $0.66 and $1.98. Cost per solved task is known for DeepSeek V4 Pro 0813 only.

Which has the bigger context window, Claude Sonnet 5.5 or DeepSeek V4 Pro 0813?

DeepSeek V4 Pro 0813, with 1.05M tokens against 1M.

How many benchmarks is the Claude Sonnet 5.5 vs DeepSeek V4 Pro 0813 comparison based on?

62 benchmarks have a result for both models as of October 21, 2026. Claude Sonnet 5.5's coding index rests on 2 independent benchmarks and DeepSeek V4 Pro 0813's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next