LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Sonnet 4.5 vs DeepSeek V4 Pro 0813

Updated October 21, 2026. 55 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 DeepSeek V4 Pro 0813
Claude Sonnet 4.5Anthropic
Coding
59.1
Overall
20.7
Output $/M
$15.00
19
DeepSeek V4 Pro 0813DeepSeek
Coding
54.6
Overall
36.0
Output $/M
$1.98
36
vs boards won of 55 shared

Decision reading

Pick Claude Sonnet 4.5 for coding: it scores 59.1 on the Vibe Coding Index against 54.6 for DeepSeek V4 Pro 0813.

Pick DeepSeek V4 Pro 0813 when output tokens cost 7.6x less, or when a solved task costs $0.10 against $1.16.

Model AClaude Sonnet 4.5Anthropic59.1/1002 independent benchmarks$1.16 per solved taskModel BDeepSeek V4 Pro 0813DeepSeek54.6/1001 independent benchmark$0.10 per solved task
Shared results
55
Claude Sonnet 4.5 only
37
DeepSeek V4 Pro 0813 only
23
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 4.5 59.1 from 2 benchmarks, DeepSeek V4 Pro 0813 54.6 from 1 benchmark.
Widest category
Agentic work, 25.5 points apart on average over 1 shared benchmark.
Widest single gap
Vibe Code Bench (Vals AI): Claude Sonnet 4.5 22.6% against DeepSeek V4 Pro 0813 82.3%, 59.7 points apart on a 0 to 100 scale.
Output price
Claude Sonnet 4.5 $15.00 against DeepSeek V4 Pro 0813 $1.98 per million output tokens, 7.6x apart.
Context window
Claude Sonnet 4.5 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 4.5BarsDeepSeek V4 Pro 0813Ties
Coding28
Intelligence02
Agentic work01
Reasoning36
Math24
Knowledge46
General89
All shared boards1936
CodingLike-for-likeFour of these boards feed the Vibe Coding Index28
Coding benchmarks for Claude Sonnet 4.5 and DeepSeek V4 Pro 0813
BenchmarkClaude Sonnet 4.5DeepSeek V4 Pro 0813Leader
SWE-bench Verified74.8%Not measuredOnly Claude Sonnet 4.5 measured
SWE-bench Multilingual67.0%Not measuredOnly Claude Sonnet 4.5 measured
LMArena WebDev13941582DeepSeek V4 Pro 0813
AA Coding Index52.168.8DeepSeek V4 Pro 0813
LiveCodeBench (Vals AI)73.0%87.5%DeepSeek V4 Pro 0813
SWE-bench Verified (Vals AI)70.0%96.4%DeepSeek V4 Pro 0813
Terminal-Bench 4 (Vals AI)Not measured14.1%Only DeepSeek V4 Pro 0813 measured
Vibe Code Bench (Vals AI)22.6%82.3%DeepSeek V4 Pro 0813
Code migration (Vals AI)Not measured41.5%Only DeepSeek V4 Pro 0813 measured
ProgramBench (Vals AI)Not measured0.0%Only DeepSeek V4 Pro 0813 measured
IOI (Vals AI)Not measured51.6%Only DeepSeek V4 Pro 0813 measured
Terminal-Bench 2.1 (Vals AI)Not measured54.7%Only DeepSeek V4 Pro 0813 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)Not measured72.9%Only DeepSeek V4 Pro 0813 measured
SciCodeNot measured51.0%Only DeepSeek V4 Pro 0813 measured
Terminal-Bench46.5%Not measuredOnly Claude Sonnet 4.5 measured
FrontierCodeNot measured28.5%Only DeepSeek V4 Pro 0813 measured
GSO-Bench14.7%Not measuredOnly Claude Sonnet 4.5 measured
WeirdML47.7%66.2%DeepSeek V4 Pro 0813
Cybench60.0%Not measuredOnly Claude Sonnet 4.5 measured
ALE-BenchNot measured1403.2Only DeepSeek V4 Pro 0813 measured
LMArena Text: coding14881469Claude Sonnet 4.5
LMArena Text: software and IT14731462Claude Sonnet 4.5
LMArena WebDev: React13861588DeepSeek V4 Pro 0813
LMArena WebDev: HTML13991566DeepSeek V4 Pro 0813
Neither model has a result on the other 12 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
Intelligence benchmarks for Claude Sonnet 4.5 and DeepSeek V4 Pro 0813
BenchmarkClaude Sonnet 4.5DeepSeek V4 Pro 0813Leader
AA Intelligence Index20.736.0DeepSeek V4 Pro 0813
Epoch Capabilities Index146.7155.6DeepSeek V4 Pro 0813
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
Agentic work benchmarks for Claude Sonnet 4.5 and DeepSeek V4 Pro 0813
BenchmarkClaude Sonnet 4.5DeepSeek V4 Pro 0813Leader
AA Agentic Index15.841.3DeepSeek V4 Pro 0813
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
SREBench (Vals AI)Not measured1.9%Only DeepSeek V4 Pro 0813 measured
Finance Agent (Vals AI)Not measured50.4%Only DeepSeek V4 Pro 0813 measured
Tax Agent Bench (Vals AI)Not measured26.8%Only DeepSeek V4 Pro 0813 measured
Legal Research Bench (Vals AI)Not measured40.9%Only DeepSeek V4 Pro 0813 measured
Harvey's Legal Agent Benchmark (Vals AI)Not measured10.8%Only DeepSeek V4 Pro 0813 measured
Excel Modeling Benchmark (Vals AI)Not measured52.8%Only DeepSeek V4 Pro 0813 measured
Terminal-Bench-Science (Vals AI)Not measured4.3%Only DeepSeek V4 Pro 0813 measured
APEX-AgentsNot measured47.3%Only DeepSeek V4 Pro 0813 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$3,839Not measuredOnly Claude Sonnet 4.5 measured
Neither model has a result on the other 21 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index36
Reasoning benchmarks for Claude Sonnet 4.5 and DeepSeek V4 Pro 0813
BenchmarkClaude Sonnet 4.5DeepSeek V4 Pro 0813Leader
GPQA Diamond81.6%92.4%DeepSeek V4 Pro 0813
MMMU Pro (Vals AI)79.3%Not measuredOnly Claude Sonnet 4.5 measured
GPQA Diamond (Artificial Analysis run)Not measured92.8%Only DeepSeek V4 Pro 0813 measured
Humanity's Last Exam (Artificial Analysis run)Not measured41.0%Only DeepSeek V4 Pro 0813 measured
GPQA Diamond (Epoch AI run)82.3%91.7%DeepSeek V4 Pro 0813
ARC-AGI63.7%90.5%DeepSeek V4 Pro 0813
ARC-AGI-213.6%61.3%DeepSeek V4 Pro 0813
SimpleBench54.3%Not measuredOnly Claude Sonnet 4.5 measured
Chess puzzles10.0%46.0%DeepSeek V4 Pro 0813
Mystery game puzzles17.0%43.0%DeepSeek V4 Pro 0813
EBR-bench2.4%Not measuredOnly Claude Sonnet 4.5 measured
VPCT39.8%Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text: hard prompts14621458Claude Sonnet 4.5
LMArena Text: expert14831459Claude Sonnet 4.5
LMArena Text: hard prompts in English14711463Claude Sonnet 4.5
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index24
Math benchmarks for Claude Sonnet 4.5 and DeepSeek V4 Pro 0813
BenchmarkClaude Sonnet 4.5DeepSeek V4 Pro 0813Leader
AIME88.2%Not measuredOnly Claude Sonnet 4.5 measured
MGSM (Vals AI)94.3%Not measuredOnly Claude Sonnet 4.5 measured
OTIS Mock AIME77.8%98.6%DeepSeek V4 Pro 0813
FrontierMath, tiers 1 to 323.9%64.6%DeepSeek V4 Pro 0813
FrontierMath, tier 42.4%26.8%DeepSeek V4 Pro 0813
ProofBench19.0%50.0%DeepSeek V4 Pro 0813
MATH level 597.7%Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text: math14491441Claude Sonnet 4.5
LMArena Text: mathematical work14621443Claude Sonnet 4.5
Neither model has a result on the other 4 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index46
Knowledge benchmarks for Claude Sonnet 4.5 and DeepSeek V4 Pro 0813
BenchmarkClaude Sonnet 4.5DeepSeek V4 Pro 0813Leader
MMLU Pro87.4%87.0%Claude Sonnet 4.5
LegalBench (Vals AI)84.1%82.4%Claude Sonnet 4.5
CaseLaw (Vals AI)62.2%Not measuredOnly Claude Sonnet 4.5 measured
CorpFin (Vals AI)62.0%65.4%DeepSeek V4 Pro 0813
TaxEval (Vals AI)73.3%73.1%Claude Sonnet 4.5
MortgageTax (Vals AI)64.0%Not measuredOnly Claude Sonnet 4.5 measured
MedQA (Vals AI)94.7%Not measuredOnly Claude Sonnet 4.5 measured
MedCode (Vals AI)44.1%42.5%Claude Sonnet 4.5
SimpleQA Verified30.7%52.9%DeepSeek V4 Pro 0813
LMArena Text: science14481457DeepSeek V4 Pro 0813
LMArena Text: medicine and healthcare14441446DeepSeek V4 Pro 0813
LMArena Text: legal and government14511459DeepSeek V4 Pro 0813
LMArena Text: business and finance14401442DeepSeek V4 Pro 0813
Neither model has a result on the other 4 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for Claude Sonnet 4.5 and DeepSeek V4 Pro 0813
BenchmarkClaude Sonnet 4.5DeepSeek V4 Pro 0813Leader
Design Arena: websites1190Not measuredOnly Claude Sonnet 4.5 measured
Design Arena: UI components1173Not measuredOnly Claude Sonnet 4.5 measured
Design Arena: game dev1166Not measuredOnly Claude Sonnet 4.5 measured
Design Arena: data viz1167Not measuredOnly Claude Sonnet 4.5 measured
Design Arena: 3D1158Not measuredOnly Claude Sonnet 4.5 measured
Design Arena: all code categories1183Not measuredOnly Claude Sonnet 4.5 measured
Design Arena: SVG1114Not measuredOnly Claude Sonnet 4.5 measured
Design Arena: ASCII art1204Not measuredOnly Claude Sonnet 4.5 measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index89
General benchmarks for Claude Sonnet 4.5 and DeepSeek V4 Pro 0813
BenchmarkClaude Sonnet 4.5DeepSeek V4 Pro 0813Leader
Vals IndexNot measured53.0%Only DeepSeek V4 Pro 0813 measured
SAGE (Vals AI)36.1%Not measuredOnly Claude Sonnet 4.5 measured
MedScribe (Vals AI)84.5%80.2%Claude Sonnet 4.5
Long context reasoning (AA-LCR)Not measured80.3%Only DeepSeek V4 Pro 0813 measured
DTBench83.2%93.9%DeepSeek V4 Pro 0813
LMCA38.8%45.5%DeepSeek V4 Pro 0813
LMArena Text14381446DeepSeek V4 Pro 0813
LMArena Text: instruction following14591448Claude Sonnet 4.5
LMArena Text: creative writing14421439Claude Sonnet 4.5
LMArena Text: English14501457DeepSeek V4 Pro 0813
LMArena Text: non-English14251431DeepSeek V4 Pro 0813
LMArena Text: Chinese14601481DeepSeek V4 Pro 0813
LMArena Text: German1427Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text: Japanese1390Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text: Korean14021449DeepSeek V4 Pro 0813
LMArena Text: French14591446Claude Sonnet 4.5
LMArena Text: Spanish14581435Claude Sonnet 4.5
LMArena Text: Russian14371448DeepSeek V4 Pro 0813
LMArena Text: Polish1423Not measuredOnly Claude Sonnet 4.5 measured
LMArena Text: multi-turn14651454Claude Sonnet 4.5
LMArena Text: longer queries14751458Claude Sonnet 4.5
LMArena Text: writing and language14421443DeepSeek V4 Pro 0813
LMArena Text: entertainment and media14281424Claude Sonnet 4.5
LMArena Document1450Not measuredOnly Claude Sonnet 4.5 measured
Neither model has a result on the other 22 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 V4 Pro 0813
BenchmarkClaude Sonnet 4.5DeepSeek 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 4.5$0.011Fits 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 4.5$0.195Fits 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 4.5$0.750Fits 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 4.5 and DeepSeek V4 Pro 0813
SpecificationAnthropic Claude Sonnet 4.5DeepSeek V4 Pro 0813
MakerAnthropicDeepSeek
WeightsNo public weights listedOpen weights
ReleasedSeptember 29, 2025August 12, 2026
Context window1M1.05M
Input $/Mtok$3.00$0.66
Output $/Mtok$15.00$1.98
Coding index59.154.6
Independent measurements behind it21
Cost per solved task$1.16$0.10
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Sonnet 4.5 better than DeepSeek V4 Pro 0813 for coding?

Pick Claude Sonnet 4.5 for coding: it scores 59.1 on the Vibe Coding Index against 54.6 for DeepSeek V4 Pro 0813. Pick DeepSeek V4 Pro 0813 when output tokens cost 7.6x less, or when a solved task costs $0.10 against $1.16.

Which is cheaper, Claude Sonnet 4.5 or DeepSeek V4 Pro 0813?

Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; DeepSeek V4 Pro 0813 costs $0.66 and $1.98. Per solved SWE-bench Verified task, Claude Sonnet 4.5 costs $1.16 and DeepSeek V4 Pro 0813 $0.10.

Which has the bigger context window, Claude Sonnet 4.5 or DeepSeek V4 Pro 0813?

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

How many benchmarks is the Claude Sonnet 4.5 vs DeepSeek V4 Pro 0813 comparison based on?

55 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 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