Claude Sonnet 4.5 vs DeepSeek V4 Flash 0731

DeepSeek V4 Flash 0731 leads Claude Sonnet 4.5 on coding, 51.8 to 39.5 on the Vibe Coding Index, and DeepSeek V4 Flash 0731 costs 37.9x less per output token ($0.396 vs $15.00 per million). Updated October 22, 2026; 36 benchmarks have a result for both.

Replace Claude Sonnet 4.5 Replace DeepSeek V4 Flash 0731

Claude Sonnet 4.5Anthropic

Coding: 39.5
Overall: 49.5
Output $/M: $15.00

DeepSeek V4 Flash 0731DeepSeek

Coding: 51.8
Overall: 55.2
Output $/M: $0.396

vs boards won of 36 shared

Claude Sonnet 4.5 or DeepSeek V4 Flash 0731: which to pick

Pick DeepSeek V4 Flash 0731 for coding: it scores 51.8 on the Vibe Coding Index against 39.5 for Claude Sonnet 4.5.

Pick Claude Sonnet 4.5 for work measured by MMLU Pro or LegalBench (Vals AI), where it leads.

Model AClaude Sonnet 4.5Anthropic39.5/1003 independent benchmarks$1.16 per solved task Model BDeepSeek V4 Flash 0731DeepSeek51.8/1004 independent benchmarks$0.01 per solved task

365919

Shared results: 36
Claude Sonnet 4.5 only: 59
DeepSeek V4 Flash 0731 only: 19
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.

Coding
Vibe Coding Index, six public coding benchmarks
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 scores 51.8 against 39.5.
3 and 4 benchmarks behind the scores
Intelligence
AA Intelligence Index
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads, 34.3 against 20.7.
Same board, both measured
Agentic work
AA Agentic Index
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads, 41.0 against 15.8.
Same board, both measured
Reasoning
GPQA Diamond
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads, 89.9% against 81.6%.
Same board, both measured
Math
AIME
No call
Only Claude Sonnet 4.5 has a AIME result, 88.2%.
Directional only
Knowledge
MMLU Pro
Claude Sonnet 4.5
Claude Sonnet 4.5 leads, 87.4% against 86.2%.
Same board, both measured
Web design
Design Arena: websites
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads, 1237 against 1189.
Same board, both measured
Long documents
Listed context window
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V4 Flash 0731
Claude Sonnet 4.5 $0.011, DeepSeek V4 Flash 0731 $0.0003 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
DeepSeek V4 Flash 0731
Claude Sonnet 4.5 $1.16, DeepSeek V4 Flash 0731 $0.01.
Published attempt cost and pass rate

At a glance

Coding index: Claude Sonnet 4.5 39.5 from 3 benchmarks, DeepSeek V4 Flash 0731 51.8 from 4 benchmarks.
Widest category: Math, 27.3 points apart on average over 4 shared benchmarks.
Widest single gap: Vibe Code Bench (Vals AI): Claude Sonnet 4.5 22.6% against DeepSeek V4 Flash 0731 74.7%, 52.1 points apart on a 0 to 100 scale.
Output price: Claude Sonnet 4.5 $15.00 against DeepSeek V4 Flash 0731 $0.396 per million output tokens, 37.9x apart.
Context window: Claude Sonnet 4.5 takes 1M tokens, DeepSeek V4 Flash 0731 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
Category	Claude Sonnet 4.5	DeepSeek V4 Flash 0731
Coding	0	5
Intelligence	0	2
Agentic work	0	1
Reasoning	0	7
Math	0	4
Knowledge	5	1
Web design	1	7
General	1	2
All shared boards	7	29

CodingLike-for-likeSix of these boards feed the Vibe Coding Index05

Coding benchmarks for Claude Sonnet 4.5 and DeepSeek V4 Flash 0731
Benchmark	Claude Sonnet 4.5	DeepSeek V4 Flash 0731	Leader
SWE-bench Verified	74.8%	Not measured	Only Claude Sonnet 4.5 measured
SWE-bench Multilingual	67.0%	Not measured	Only Claude Sonnet 4.5 measured
LMArena WebDev	1394	Not measured	Only Claude Sonnet 4.5 measured
AA Coding Index	52.1	69.1	DeepSeek V4 Flash 0731
LiveCodeBench (Vals AI)	73.0%	87.3%	DeepSeek V4 Flash 0731
SWE-bench Verified (Vals AI)	70.0%	88.8%	DeepSeek V4 Flash 0731
Terminal-Bench 4 (Vals AI)	Not measured	18.7%	Only DeepSeek V4 Flash 0731 measured
Vibe Code Bench (Vals AI)	22.6%	74.7%	DeepSeek V4 Flash 0731
Code migration (Vals AI)	Not measured	38.6%	Only DeepSeek V4 Flash 0731 measured
ProgramBench (Vals AI)	Not measured	0.0%	Only DeepSeek V4 Flash 0731 measured
IOI (Vals AI)	Not measured	32.7%	Only DeepSeek V4 Flash 0731 measured
Terminal-Bench 2.1 (Vals AI)	Not measured	67.0%	Only DeepSeek V4 Flash 0731 measured
SkillsBench (Vals AI)	Not measured	50.7%	Only DeepSeek V4 Flash 0731 measured
CyberBench (Vals AI)	Not measured	72.1%	Only DeepSeek V4 Flash 0731 measured
SciCode	Not measured	50.3%	Only DeepSeek V4 Flash 0731 measured
Terminal-Bench	46.5%	Not measured	Only Claude Sonnet 4.5 measured
FrontierCode	Not measured	18.8%	Only DeepSeek V4 Flash 0731 measured
GSO-Bench	14.7%	Not measured	Only Claude Sonnet 4.5 measured
WeirdML	47.7%	63.0%	DeepSeek V4 Flash 0731
Cybench	60.0%	Not measured	Only Claude Sonnet 4.5 measured
ALE-Bench	Not measured	1306.1	Only DeepSeek V4 Flash 0731 measured
LMArena Text: coding	1488	Not measured	Only Claude Sonnet 4.5 measured
LMArena Text: software and IT	1473	Not measured	Only Claude Sonnet 4.5 measured
LMArena WebDev: React	1386	Not measured	Only Claude Sonnet 4.5 measured
LMArena WebDev: HTML	1399	Not measured	Only Claude Sonnet 4.5 measured
Neither model has a result on the other 14 boards here

IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02

Intelligence benchmarks for Claude Sonnet 4.5 and DeepSeek V4 Flash 0731
Benchmark	Claude Sonnet 4.5	DeepSeek V4 Flash 0731	Leader
AA Intelligence Index	20.7	34.3	DeepSeek V4 Flash 0731
Epoch Capabilities Index	146.7	154.8	DeepSeek V4 Flash 0731

Agentic workLike-for-likePublic boards, shown as published, kept out of the index01

Agentic work benchmarks for Claude Sonnet 4.5 and DeepSeek V4 Flash 0731
Benchmark	Claude Sonnet 4.5	DeepSeek V4 Flash 0731	Leader
AA Agentic Index	15.8	41.0	DeepSeek V4 Flash 0731
Design Arena: agents building web apps	1060	Not measured	Only Claude Sonnet 4.5 measured
Design Arena: agents building full-stack apps	1050	Not measured	Only Claude Sonnet 4.5 measured
Design Arena: agents building mobile apps	1137	Not measured	Only Claude Sonnet 4.5 measured
Finance Agent (Vals AI)	Not measured	49.5%	Only DeepSeek V4 Flash 0731 measured
Tax Agent Bench (Vals AI)	Not measured	28.1%	Only DeepSeek V4 Flash 0731 measured
Legal Research Bench (Vals AI)	Not measured	30.3%	Only DeepSeek V4 Flash 0731 measured
Excel Modeling Benchmark (Vals AI)	Not measured	57.0%	Only DeepSeek V4 Flash 0731 measured
BioMysteryBench (Vals AI)	Not measured	64.4%	Only DeepSeek V4 Flash 0731 measured
Terminal-Bench-Science (Vals AI)	Not measured	4.3%	Only DeepSeek V4 Flash 0731 measured
METR time horizons	67.4%	Not measured	Only Claude Sonnet 4.5 measured
Remote Labor Index	2.1%	Not measured	Only Claude Sonnet 4.5 measured
GDPval	42.5%	Not measured	Only Claude Sonnet 4.5 measured
DeepResearch Bench	52.6%	Not measured	Only Claude Sonnet 4.5 measured
OSWorld	62.9%	Not measured	Only Claude Sonnet 4.5 measured
Vending-Bench 2	$3,839	Not measured	Only Claude Sonnet 4.5 measured
Berkeley Function Calling Leaderboard (BFCL)	73.2%	Not measured	Only Claude Sonnet 4.5 measured
Neither model has a result on the other 24 boards here

ReasoningLike-for-likePublic boards, shown as published, kept out of the index07

Reasoning benchmarks for Claude Sonnet 4.5 and DeepSeek V4 Flash 0731
Benchmark	Claude Sonnet 4.5	DeepSeek V4 Flash 0731	Leader
GPQA Diamond	81.6%	89.9%	DeepSeek V4 Flash 0731
MMMU Pro (Vals AI)	79.3%	Not measured	Only Claude Sonnet 4.5 measured
GPQA Diamond (Artificial Analysis run)	Not measured	90.8%	Only DeepSeek V4 Flash 0731 measured
Humanity's Last Exam (Artificial Analysis run)	Not measured	38.6%	Only DeepSeek V4 Flash 0731 measured
GPQA Diamond (Epoch AI run)	82.3%	91.0%	DeepSeek V4 Flash 0731
ARC-AGI	63.7%	89.0%	DeepSeek V4 Flash 0731
ARC-AGI-2	13.6%	61.4%	DeepSeek V4 Flash 0731
SimpleBench	54.3%	61.1%	DeepSeek V4 Flash 0731
Chess puzzles	10.0%	32.0%	DeepSeek V4 Flash 0731
Mystery game puzzles	17.0%	34.0%	DeepSeek V4 Flash 0731
EBR-bench	2.4%	Not measured	Only Claude Sonnet 4.5 measured
VPCT	39.8%	Not measured	Only Claude Sonnet 4.5 measured
LMArena Text: hard prompts	1462	Not measured	Only Claude Sonnet 4.5 measured
LMArena Text: expert	1483	Not measured	Only Claude Sonnet 4.5 measured
LMArena Text: hard prompts in English	1471	Not measured	Only Claude Sonnet 4.5 measured
Kagi LLM Benchmark	57.9%	Not measured	Only 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 index04

Math benchmarks for Claude Sonnet 4.5 and DeepSeek V4 Flash 0731
Benchmark	Claude Sonnet 4.5	DeepSeek V4 Flash 0731	Leader
AIME	88.2%	Not measured	Only Claude Sonnet 4.5 measured
MGSM (Vals AI)	94.3%	Not measured	Only Claude Sonnet 4.5 measured
OTIS Mock AIME	77.8%	94.4%	DeepSeek V4 Flash 0731
FrontierMath, tiers 1 to 3	23.9%	57.5%	DeepSeek V4 Flash 0731
FrontierMath, tier 4	2.4%	24.4%	DeepSeek V4 Flash 0731
ProofBench	19.0%	56.0%	DeepSeek V4 Flash 0731
MATH level 5	97.7%	Not measured	Only Claude Sonnet 4.5 measured
LMArena Text: math	1449	Not measured	Only Claude Sonnet 4.5 measured
LMArena Text: mathematical work	1462	Not measured	Only Claude Sonnet 4.5 measured
Neither model has a result on the other 4 boards here

KnowledgeLike-for-likePublic boards, shown as published, kept out of the index51

Knowledge benchmarks for Claude Sonnet 4.5 and DeepSeek V4 Flash 0731
Benchmark	Claude Sonnet 4.5	DeepSeek V4 Flash 0731	Leader
MMLU Pro	87.4%	86.2%	Claude Sonnet 4.5
LegalBench (Vals AI)	84.1%	77.7%	Claude Sonnet 4.5
CaseLaw (Vals AI)	62.2%	Not measured	Only Claude Sonnet 4.5 measured
CorpFin (Vals AI)	62.0%	61.9%	Claude Sonnet 4.5
TaxEval (Vals AI)	73.3%	70.7%	Claude Sonnet 4.5
MortgageTax (Vals AI)	64.0%	Not measured	Only Claude Sonnet 4.5 measured
MedQA (Vals AI)	94.7%	Not measured	Only Claude Sonnet 4.5 measured
MedCode (Vals AI)	44.1%	41.4%	Claude Sonnet 4.5
SimpleQA Verified	30.7%	33.6%	DeepSeek V4 Flash 0731
LMArena Text: science	1448	Not measured	Only Claude Sonnet 4.5 measured
LMArena Text: medicine and healthcare	1444	Not measured	Only Claude Sonnet 4.5 measured
LMArena Text: legal and government	1451	Not measured	Only Claude Sonnet 4.5 measured
LMArena Text: business and finance	1440	Not measured	Only Claude Sonnet 4.5 measured
FACTS Benchmark Suite	40.6%	Not measured	Only Claude Sonnet 4.5 measured
Neither model has a result on the other 4 boards here

Web designLike-for-likePublic boards, shown as published, kept out of the index17

Web design benchmarks for Claude Sonnet 4.5 and DeepSeek V4 Flash 0731
Benchmark	Claude Sonnet 4.5	DeepSeek V4 Flash 0731	Leader
Design Arena: websites	1189	1237	DeepSeek V4 Flash 0731
Design Arena: UI components	1170	1233	DeepSeek V4 Flash 0731
Design Arena: game dev	1166	1207	DeepSeek V4 Flash 0731
Design Arena: data viz	1167	1180	DeepSeek V4 Flash 0731
Design Arena: 3D	1157	1208	DeepSeek V4 Flash 0731
Design Arena: all code categories	1182	1229	DeepSeek V4 Flash 0731
Design Arena: SVG	1115	1184	DeepSeek V4 Flash 0731
Design Arena: ASCII art	1205	1090	Claude 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 index12

General benchmarks for Claude Sonnet 4.5 and DeepSeek V4 Flash 0731
Benchmark	Claude Sonnet 4.5	DeepSeek V4 Flash 0731	Leader
SAGE (Vals AI)	36.1%	Not measured	Only Claude Sonnet 4.5 measured
MedScribe (Vals AI)	84.5%	80.4%	Claude Sonnet 4.5
Long context reasoning (AA-LCR)	Not measured	79.7%	Only DeepSeek V4 Flash 0731 measured
DTBench	83.2%	90.9%	DeepSeek V4 Flash 0731
LMCA	38.8%	41.7%	DeepSeek V4 Flash 0731
LMArena Text	1438	Not measured	Only Claude Sonnet 4.5 measured
LMArena Text: instruction following	1459	Not measured	Only Claude Sonnet 4.5 measured
LMArena Text: creative writing	1442	Not measured	Only Claude Sonnet 4.5 measured
LMArena Text: English	1450	Not measured	Only Claude Sonnet 4.5 measured
LMArena Text: non-English	1425	Not measured	Only Claude Sonnet 4.5 measured
LMArena Text: Chinese	1460	Not measured	Only Claude Sonnet 4.5 measured
LMArena Text: German	1427	Not measured	Only Claude Sonnet 4.5 measured
LMArena Text: Japanese	1390	Not measured	Only Claude Sonnet 4.5 measured
LMArena Text: Korean	1402	Not measured	Only Claude Sonnet 4.5 measured
LMArena Text: French	1459	Not measured	Only Claude Sonnet 4.5 measured
LMArena Text: Spanish	1458	Not measured	Only Claude Sonnet 4.5 measured
LMArena Text: Russian	1437	Not measured	Only Claude Sonnet 4.5 measured
LMArena Text: Polish	1423	Not measured	Only Claude Sonnet 4.5 measured
LMArena Text: multi-turn	1465	Not measured	Only Claude Sonnet 4.5 measured
LMArena Text: longer queries	1475	Not measured	Only Claude Sonnet 4.5 measured
LMArena Text: writing and language	1442	Not measured	Only Claude Sonnet 4.5 measured
LMArena Text: entertainment and media	1428	Not measured	Only Claude Sonnet 4.5 measured
LMArena Document	1450	Not measured	Only Claude Sonnet 4.5 measured
Neither model has a result on the other 23 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 Flash 0731
Benchmark	Claude Sonnet 4.5	DeepSeek V4 Flash 0731	Leader
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 Flash 0731$0.0003Fits in one request

DeepSeek V4 Flash 0731 costs less

Repository review

50K input + 3K output tokens

Claude Sonnet 4.5$0.195Fits in one request

DeepSeek V4 Flash 0731$0.0082Fits in one request

DeepSeek V4 Flash 0731 costs less

Agent loop

200K input + 10K output tokens

Claude Sonnet 4.5$0.750Fits in one request

DeepSeek V4 Flash 0731$0.032Fits in one request

DeepSeek V4 Flash 0731 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 Flash 0731
Specification	Anthropic Claude Sonnet 4.5	DeepSeek V4 Flash 0731
Maker	Anthropic	DeepSeek
Weights	No public weights listed	Open weights
Released	September 29, 2025	July 31, 2026
Context window	1M	1.05M
Input $/Mtok	$3.00	$0.14
Output $/Mtok	$15.00	$0.396
Coding index	39.5	51.8
Independent measurements behind it	3	4
Cost per solved task	$1.16	$0.01
Source	OpenRouter listing	OpenRouter listing

Questions

Is Claude Sonnet 4.5 better than DeepSeek V4 Flash 0731 for coding?

Pick DeepSeek V4 Flash 0731 for coding: it scores 51.8 on the Vibe Coding Index against 39.5 for Claude Sonnet 4.5. Pick Claude Sonnet 4.5 for work measured by MMLU Pro or LegalBench (Vals AI), where it leads.

Which is cheaper, Claude Sonnet 4.5 or DeepSeek V4 Flash 0731?

Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; DeepSeek V4 Flash 0731 costs $0.14 and $0.396. Per solved SWE-bench Verified task, Claude Sonnet 4.5 costs $1.16 and DeepSeek V4 Flash 0731 $0.01.

Which has the bigger context window, Claude Sonnet 4.5 or DeepSeek V4 Flash 0731?

DeepSeek V4 Flash 0731, with 1.05M tokens against 1M.

How many benchmarks is the Claude Sonnet 4.5 vs DeepSeek V4 Flash 0731 comparison based on?

36 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 V4 Flash 0731's on 4. 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-v4-flash-0731" title="Claude Sonnet 4.5 vs DeepSeek V4 Flash 0731, 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-v4-flash-0731">LLMBenchmark.ai, Claude Sonnet 4.5 vs DeepSeek V4 Flash 0731</a></p>

Claude Sonnet 4.5 or DeepSeek V4 Flash 0731: which to pick

Which one for your work

Coding

Intelligence

Agentic work

Reasoning

Math

Knowledge

Web design

Long documents

Everyday cost

Cost per solved task

At a glance

Benchmark by benchmark

What each workload costs

Chat turn

Repository review

Agent loop

Specification differences

Questions

Compare next