Claude Haiku 4.5 vs DeepSeek V4 Flash 0731

DeepSeek V4 Flash 0731 leads Claude Haiku 4.5 on coding, 51.8 to 35.6 on the Vibe Coding Index, and DeepSeek V4 Flash 0731 costs 12.6x less per output token ($0.396 vs $5.00 per million). Updated October 22, 2026; 38 benchmarks have a result for both.

Replace Claude Haiku 4.5 Replace DeepSeek V4 Flash 0731

Claude Haiku 4.5Anthropic

Coding: 35.6
Overall: 41.0
Output $/M: $5.00

DeepSeek V4 Flash 0731DeepSeek

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

vs boards won of 38 shared, 1 tied

Claude Haiku 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 35.6 for Claude Haiku 4.5.

Pick Claude Haiku 4.5 for work measured by LegalBench (Vals AI) or Design Arena: ASCII art, where it leads.

Model AClaude Haiku 4.5Anthropic35.6/1004 independent benchmarks$0.56 per solved task Model BDeepSeek V4 Flash 0731DeepSeek51.8/1004 independent benchmarks$0.01 per solved task

385717

Shared results: 38
Claude Haiku 4.5 only: 57
DeepSeek V4 Flash 0731 only: 17
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 35.6.
4 benchmarks behind each score
Intelligence
AA Intelligence Index
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads, 34.3 against 16.9.
Same board, both measured
Agentic work
AA Agentic Index
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads, 41.0 against 8.0.
Same board, both measured
Reasoning
GPQA Diamond
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads, 89.9% against 72.2%.
Same board, both measured
Math
AIME
No call
Only Claude Haiku 4.5 has a AIME result, 82.7%.
Directional only
Knowledge
MMLU Pro
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads, 86.2% against 78.7%.
Same board, both measured
Web design
Design Arena: websites
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 leads, 1237 against 1122.
Same board, both measured
Long documents
Listed context window
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 takes 1.05M tokens against 200K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V4 Flash 0731
Claude Haiku 4.5 $0.0035, 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 Haiku 4.5 $0.56, DeepSeek V4 Flash 0731 $0.01.
Published attempt cost and pass rate

At a glance

Coding index: Claude Haiku 4.5 35.6 from 4 benchmarks, DeepSeek V4 Flash 0731 51.8 from 4 benchmarks.
Widest category: Reasoning, 32.0 points apart on average over 5 shared benchmarks.
Widest single gap: Vibe Code Bench (Vals AI): Claude Haiku 4.5 11.4% against DeepSeek V4 Flash 0731 74.7%, 63.3 points apart on a 0 to 100 scale.
Output price: Claude Haiku 4.5 $5.00 against DeepSeek V4 Flash 0731 $0.396 per million output tokens, 12.6x apart.
Context window: Claude Haiku 4.5 takes 200K 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 Haiku 4.5	DeepSeek V4 Flash 0731	Ties
Coding	0	7	1 tie
Intelligence	0	2
Agentic work	0	5
Reasoning	0	5
Math	0	1
Knowledge	1	5
Web design	1	7
General	1	2
All shared boards	3	34	1 tie

CodingLike-for-likeSix of these boards feed the Vibe Coding Index07

Coding benchmarks for Claude Haiku 4.5 and DeepSeek V4 Flash 0731
Benchmark	Claude Haiku 4.5	DeepSeek V4 Flash 0731	Leader
SWE-bench Verified	66.6%	Not measured	Only Claude Haiku 4.5 measured
SWE-bench Multilingual	64.7%	Not measured	Only Claude Haiku 4.5 measured
LiveBench coding	48.1%	Not measured	Only Claude Haiku 4.5 measured
LMArena WebDev	1330	Not measured	Only Claude Haiku 4.5 measured
AA Coding Index	43.9	69.1	DeepSeek V4 Flash 0731
LiveCodeBench (Vals AI)	41.2%	87.3%	DeepSeek V4 Flash 0731
SWE-bench Verified (Vals AI)	66.6%	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)	11.4%	74.7%	DeepSeek V4 Flash 0731
Code migration (Vals AI)	7.5%	38.6%	DeepSeek V4 Flash 0731
ProgramBench (Vals AI)	0.0%	0.0%	Tie
IOI (Vals AI)	Not measured	32.7%	Only DeepSeek V4 Flash 0731 measured
Terminal-Bench 2.1 (Vals AI)	43.8%	67.0%	DeepSeek V4 Flash 0731
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	35.5%	Not measured	Only Claude Haiku 4.5 measured
FrontierCode	Not measured	18.8%	Only DeepSeek V4 Flash 0731 measured
WeirdML	45.4%	63.0%	DeepSeek V4 Flash 0731
ALE-Bench	Not measured	1306.1	Only DeepSeek V4 Flash 0731 measured
LMArena Text: coding	1454	Not measured	Only Claude Haiku 4.5 measured
LMArena Text: software and IT	1439	Not measured	Only Claude Haiku 4.5 measured
LMArena WebDev: React	1326	Not measured	Only Claude Haiku 4.5 measured
LMArena WebDev: HTML	1318	Not measured	Only Claude Haiku 4.5 measured
Neither model has a result on the other 15 boards here

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

Intelligence benchmarks for Claude Haiku 4.5 and DeepSeek V4 Flash 0731
Benchmark	Claude Haiku 4.5	DeepSeek V4 Flash 0731	Leader
AA Intelligence Index	16.9	34.3	DeepSeek V4 Flash 0731
Epoch Capabilities Index	142.2	154.8	DeepSeek V4 Flash 0731

Agentic workLike-for-likePublic boards, shown as published, kept out of the index05

Agentic work benchmarks for Claude Haiku 4.5 and DeepSeek V4 Flash 0731
Benchmark	Claude Haiku 4.5	DeepSeek V4 Flash 0731	Leader
AA Agentic Index	8.0	41.0	DeepSeek V4 Flash 0731
LiveBench research	42.2%	Not measured	Only Claude Haiku 4.5 measured
LiveBench browser	40.0%	Not measured	Only Claude Haiku 4.5 measured
LiveBench long agentic	11.1%	Not measured	Only Claude Haiku 4.5 measured
Finance Agent (Vals AI)	31.0%	49.5%	DeepSeek V4 Flash 0731
Tax Agent Bench (Vals AI)	5.9%	28.1%	DeepSeek V4 Flash 0731
Legal Research Bench (Vals AI)	10.6%	30.3%	DeepSeek V4 Flash 0731
Excel Modeling Benchmark (Vals AI)	22.7%	57.0%	DeepSeek V4 Flash 0731
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
BALROG	31.2%	Not measured	Only Claude Haiku 4.5 measured
DeepResearch Bench	45.5%	Not measured	Only Claude Haiku 4.5 measured
Vending-Bench 2	$459	Not measured	Only Claude Haiku 4.5 measured
Berkeley Function Calling Leaderboard (BFCL)	68.7%	Not measured	Only Claude Haiku 4.5 measured
Neither model has a result on the other 27 boards here

ReasoningLike-for-likePublic boards, shown as published, kept out of the index05

Reasoning benchmarks for Claude Haiku 4.5 and DeepSeek V4 Flash 0731
Benchmark	Claude Haiku 4.5	DeepSeek V4 Flash 0731	Leader
GPQA Diamond	72.2%	89.9%	DeepSeek V4 Flash 0731
LiveBench reasoning	61.7%	Not measured	Only Claude Haiku 4.5 measured
MMMU Pro (Vals AI)	46.1%	Not measured	Only Claude Haiku 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)	71.2%	91.0%	DeepSeek V4 Flash 0731
ARC-AGI	47.7%	89.0%	DeepSeek V4 Flash 0731
ARC-AGI-2	4.0%	61.4%	DeepSeek V4 Flash 0731
SimpleBench	Not measured	61.1%	Only DeepSeek V4 Flash 0731 measured
Chess puzzles	8.0%	32.0%	DeepSeek V4 Flash 0731
Mystery game puzzles	Not measured	34.0%	Only DeepSeek V4 Flash 0731 measured
LMArena Text: hard prompts	1421	Not measured	Only Claude Haiku 4.5 measured
LMArena Text: expert	1443	Not measured	Only Claude Haiku 4.5 measured
LMArena Text: hard prompts in English	1435	Not measured	Only Claude Haiku 4.5 measured
Neither model has a result on the other 8 boards here

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

Math benchmarks for Claude Haiku 4.5 and DeepSeek V4 Flash 0731
Benchmark	Claude Haiku 4.5	DeepSeek V4 Flash 0731	Leader
AIME	82.7%	Not measured	Only Claude Haiku 4.5 measured
MGSM (Vals AI)	92.2%	Not measured	Only Claude Haiku 4.5 measured
OTIS Mock AIME	66.7%	94.4%	DeepSeek V4 Flash 0731
FrontierMath, tiers 1 to 3	Not measured	57.5%	Only DeepSeek V4 Flash 0731 measured
FrontierMath, tier 4	Not measured	24.4%	Only DeepSeek V4 Flash 0731 measured
ProofBench	Not measured	56.0%	Only DeepSeek V4 Flash 0731 measured
MATH level 5	96.4%	Not measured	Only Claude Haiku 4.5 measured
LMArena Text: math	1398	Not measured	Only Claude Haiku 4.5 measured
LMArena Text: mathematical work	1430	Not measured	Only Claude Haiku 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 index15

Knowledge benchmarks for Claude Haiku 4.5 and DeepSeek V4 Flash 0731
Benchmark	Claude Haiku 4.5	DeepSeek V4 Flash 0731	Leader
MMLU Pro	78.7%	86.2%	DeepSeek V4 Flash 0731
LegalBench (Vals AI)	81.2%	77.7%	Claude Haiku 4.5
CaseLaw (Vals AI)	56.5%	Not measured	Only Claude Haiku 4.5 measured
CorpFin (Vals AI)	60.6%	61.9%	DeepSeek V4 Flash 0731
TaxEval (Vals AI)	67.5%	70.7%	DeepSeek V4 Flash 0731
MortgageTax (Vals AI)	62.2%	Not measured	Only Claude Haiku 4.5 measured
MedQA (Vals AI)	79.6%	Not measured	Only Claude Haiku 4.5 measured
MedCode (Vals AI)	32.7%	41.4%	DeepSeek V4 Flash 0731
SimpleQA Verified	13.2%	33.6%	DeepSeek V4 Flash 0731
LMArena Text: science	1406	Not measured	Only Claude Haiku 4.5 measured
LMArena Text: medicine and healthcare	1394	Not measured	Only Claude Haiku 4.5 measured
LMArena Text: legal and government	1400	Not measured	Only Claude Haiku 4.5 measured
LMArena Text: business and finance	1400	Not measured	Only Claude Haiku 4.5 measured
Neither model has a result on the other 5 boards here

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

Web design benchmarks for Claude Haiku 4.5 and DeepSeek V4 Flash 0731
Benchmark	Claude Haiku 4.5	DeepSeek V4 Flash 0731	Leader
Design Arena: websites	1122	1237	DeepSeek V4 Flash 0731
Design Arena: UI components	1097	1233	DeepSeek V4 Flash 0731
Design Arena: game dev	1097	1207	DeepSeek V4 Flash 0731
Design Arena: data viz	1124	1180	DeepSeek V4 Flash 0731
Design Arena: 3D	1071	1208	DeepSeek V4 Flash 0731
Design Arena: all code categories	1114	1229	DeepSeek V4 Flash 0731
Design Arena: SVG	1025	1184	DeepSeek V4 Flash 0731
Design Arena: ASCII art	1140	1090	Claude Haiku 4.5
LiveBench design	59.9%	Not measured	Only Claude Haiku 4.5 measured

GeneralLike-for-likePublic boards, shown as published, kept out of the index12

General benchmarks for Claude Haiku 4.5 and DeepSeek V4 Flash 0731
Benchmark	Claude Haiku 4.5	DeepSeek V4 Flash 0731	Leader
LiveBench data analysis	59.3%	Not measured	Only Claude Haiku 4.5 measured
Public Benefits Bench (Vals AI)	54.3%	Not measured	Only Claude Haiku 4.5 measured
SAGE (Vals AI)	31.8%	Not measured	Only Claude Haiku 4.5 measured
MedScribe (Vals AI)	85.2%	80.4%	Claude Haiku 4.5
Vals Multimodal Index	42.9%	Not measured	Only Claude Haiku 4.5 measured
Long context reasoning (AA-LCR)	Not measured	79.7%	Only DeepSeek V4 Flash 0731 measured
DTBench	73.6%	90.9%	DeepSeek V4 Flash 0731
LMCA	30.9%	41.7%	DeepSeek V4 Flash 0731
ExploitBench	13.7%	Not measured	Only Claude Haiku 4.5 measured
LMArena Text	1397	Not measured	Only Claude Haiku 4.5 measured
LMArena Text: instruction following	1414	Not measured	Only Claude Haiku 4.5 measured
LMArena Text: creative writing	1371	Not measured	Only Claude Haiku 4.5 measured
LMArena Text: English	1414	Not measured	Only Claude Haiku 4.5 measured
LMArena Text: non-English	1377	Not measured	Only Claude Haiku 4.5 measured
LMArena Text: Chinese	1418	Not measured	Only Claude Haiku 4.5 measured
LMArena Text: German	1374	Not measured	Only Claude Haiku 4.5 measured
LMArena Text: Japanese	1338	Not measured	Only Claude Haiku 4.5 measured
LMArena Text: Korean	1346	Not measured	Only Claude Haiku 4.5 measured
LMArena Text: French	1411	Not measured	Only Claude Haiku 4.5 measured
LMArena Text: Spanish	1421	Not measured	Only Claude Haiku 4.5 measured
LMArena Text: Russian	1381	Not measured	Only Claude Haiku 4.5 measured
LMArena Text: Polish	1343	Not measured	Only Claude Haiku 4.5 measured
LMArena Text: multi-turn	1409	Not measured	Only Claude Haiku 4.5 measured
LMArena Text: longer queries	1427	Not measured	Only Claude Haiku 4.5 measured
LMArena Text: writing and language	1386	Not measured	Only Claude Haiku 4.5 measured
LMArena Text: entertainment and media	1369	Not measured	Only Claude Haiku 4.5 measured
LMArena Document	1420	Not measured	Only Claude Haiku 4.5 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 Haiku 4.5 and DeepSeek V4 Flash 0731
Benchmark	Claude Haiku 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 Haiku 4.5$0.0035Fits 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 Haiku 4.5$0.065Fits 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 Haiku 4.5$0.250Exceeds the context window

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 Haiku 4.5 and DeepSeek V4 Flash 0731
Specification	Anthropic Claude Haiku 4.5	DeepSeek V4 Flash 0731
Maker	Anthropic	DeepSeek
Weights	No public weights listed	Open weights
Released	October 15, 2025	July 31, 2026
Context window	200K	1.05M
Input $/Mtok	$1.00	$0.14
Output $/Mtok	$5.00	$0.396
Coding index	35.6	51.8
Independent measurements behind it	4	4
Cost per solved task	$0.56	$0.01
Source	OpenRouter listing	OpenRouter listing

Questions

Is Claude Haiku 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 35.6 for Claude Haiku 4.5. Pick Claude Haiku 4.5 for work measured by LegalBench (Vals AI) or Design Arena: ASCII art, where it leads.

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

Claude Haiku 4.5 costs $1.00 per million input tokens and $5.00 per million output tokens; DeepSeek V4 Flash 0731 costs $0.14 and $0.396. Per solved SWE-bench Verified task, Claude Haiku 4.5 costs $0.56 and DeepSeek V4 Flash 0731 $0.01.

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

DeepSeek V4 Flash 0731, with 1.05M tokens against 200K.

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

38 benchmarks have a result for both models as of October 22, 2026. Claude Haiku 4.5's coding index rests on 4 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-haiku-4-5-vs-deepseek-v4-flash-0731" title="Claude Haiku 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-haiku-4-5-vs-deepseek-v4-flash-0731">LLMBenchmark.ai, Claude Haiku 4.5 vs DeepSeek V4 Flash 0731</a></p>

Claude Haiku 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