Claude Opus 4.5 vs DeepSeek V4 Pro 0423

Claude Opus 4.5 leads DeepSeek V4 Pro 0423 on coding, 44.0 to 38.7 on the Vibe Coding Index, and DeepSeek V4 Pro 0423 costs 9.2x less per output token ($2.716 vs $25.00 per million). Updated October 21, 2026; 67 benchmarks have a result for both.

Replace Claude Opus 4.5 Replace DeepSeek V4 Pro 0423

Claude Opus 4.5Anthropic

Coding: 44.0
Overall: 55.7
Output $/M: $25.00

DeepSeek V4 Pro 0423DeepSeek

Coding: 38.7
Overall: 50.0
Output $/M: $2.716

vs boards won of 67 shared, 1 tied

Claude Opus 4.5 or DeepSeek V4 Pro 0423: which to pick

Pick Claude Opus 4.5 for coding: it scores 44.0 on the Vibe Coding Index against 38.7 for DeepSeek V4 Pro 0423, though on 3 benchmarks against 5.

Pick DeepSeek V4 Pro 0423 for output tokens 9.2x cheaper ($2.716 vs $25.00 per million) and a lower cost per solved task ($0.57 against $1.37).

Model AClaude Opus 4.5Anthropic44.0/1003 independent benchmarks$1.37 per solved task Model BDeepSeek V4 Pro 0423DeepSeek38.7/1005 independent benchmarks$0.57 per solved task

674117

Shared results: 67
Claude Opus 4.5 only: 41
DeepSeek V4 Pro 0423 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
Claude Opus 4.5
Claude Opus 4.5 scores 44.0 against 38.7.
3 and 5 benchmarks behind the scores
Intelligence
AA Intelligence Index
DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 leads, 30.4 against 29.1.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only DeepSeek V4 Pro 0423 has a AA Agentic Index result, 26.3.
Directional only
Reasoning
GPQA Diamond
DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 leads, 89.4% against 85.9%.
Same board, both measured
Math
AIME
No call
Only Claude Opus 4.5 has a AIME result, 95.4%.
Directional only
Knowledge
MMLU Pro
Claude Opus 4.5
Claude Opus 4.5 leads, 87.3% against 87.3%.
Same board, both measured
Web design
Design Arena: websites
Claude Opus 4.5
Claude Opus 4.5 leads, 1247 against 1234.
Same board, both measured
Long documents
Listed context window
DeepSeek V4 Pro 0423
DeepSeek V4 Pro 0423 takes 1.05M tokens against 200K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V4 Pro 0423
Claude Opus 4.5 $0.018, DeepSeek V4 Pro 0423 $0.0026 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
DeepSeek V4 Pro 0423
Claude Opus 4.5 $1.37, DeepSeek V4 Pro 0423 $0.57.
Published attempt cost and pass rate

At a glance

Coding index: Claude Opus 4.5 44.0 from 3 benchmarks, DeepSeek V4 Pro 0423 38.7 from 5 benchmarks.
Widest category: Agentic work, 18.8 points apart on average over 3 shared benchmarks.
Widest single gap: Vibe Code Bench (Vals AI): Claude Opus 4.5 20.6% against DeepSeek V4 Pro 0423 49.9%, 29.3 points apart on a 0 to 100 scale.
Output price: Claude Opus 4.5 $25.00 against DeepSeek V4 Pro 0423 $2.716 per million output tokens, 9.2x apart.
Context window: Claude Opus 4.5 takes 200K 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
Category	Claude Opus 4.5	DeepSeek V4 Pro 0423	Ties
Coding	6	3
Intelligence	1	1
Agentic work	3	0
Reasoning	5	3
Math	4	2
Knowledge	7	4
Web design	6	1	1 tie
General	9	11
All shared boards	41	25	1 tie

CodingLike-for-likeSix of these boards feed the Vibe Coding Index63

Coding benchmarks for Claude Opus 4.5 and DeepSeek V4 Pro 0423
Benchmark	Claude Opus 4.5	DeepSeek V4 Pro 0423	Leader
SWE-bench Verified	79.2%	Not measured	Only Claude Opus 4.5 measured
SWE-bench (full test set)	52.6%	Not measured	Only Claude Opus 4.5 measured
SWE-bench Multilingual	70.7%	Not measured	Only Claude Opus 4.5 measured
LMArena WebDev	1494	1447	Claude Opus 4.5
AA Coding Index	Not measured	59.4	Only DeepSeek V4 Pro 0423 measured
LiveCodeBench (Vals AI)	83.7%	87.5%	DeepSeek V4 Pro 0423
SWE-bench Verified (Vals AI)	76.4%	77.4%	DeepSeek V4 Pro 0423
Terminal-Bench 4 (Vals AI)	Not measured	11.1%	Only DeepSeek V4 Pro 0423 measured
Vibe Code Bench (Vals AI)	20.6%	49.9%	DeepSeek V4 Pro 0423
Code migration (Vals AI)	Not measured	26.2%	Only DeepSeek V4 Pro 0423 measured
ProgramBench (Vals AI)	Not measured	0.0%	Only DeepSeek V4 Pro 0423 measured
Terminal-Bench 2.1 (Vals AI)	Not measured	50.2%	Only DeepSeek V4 Pro 0423 measured
SkillsBench (Vals AI)	Not measured	51.3%	Only DeepSeek V4 Pro 0423 measured
LiveCodeBench (Artificial Analysis run)	87.1%	Not measured	Only Claude Opus 4.5 measured
Terminal-Bench Hard (Artificial Analysis run)	47.0%	Not measured	Only Claude Opus 4.5 measured
Terminal-Bench	63.1%	Not measured	Only Claude Opus 4.5 measured
FrontierCode	Not measured	17.6%	Only DeepSeek V4 Pro 0423 measured
GSO-Bench	26.5%	Not measured	Only Claude Opus 4.5 measured
WeirdML	63.7%	48.9%	Claude Opus 4.5
Cybench	82.0%	Not measured	Only Claude Opus 4.5 measured
ALE-Bench	Not measured	1006.1	Only DeepSeek V4 Pro 0423 measured
LMArena Text: coding	1503	1470	Claude Opus 4.5
LMArena Text: software and IT	1483	1469	Claude Opus 4.5
LMArena WebDev: React	1478	1441	Claude Opus 4.5
LMArena WebDev: HTML	1510	1435	Claude Opus 4.5
Neither model has a result on the other 14 boards here

IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11

Intelligence benchmarks for Claude Opus 4.5 and DeepSeek V4 Pro 0423
Benchmark	Claude Opus 4.5	DeepSeek V4 Pro 0423	Leader
AA Intelligence Index	29.1	30.4	DeepSeek V4 Pro 0423
Epoch Capabilities Index	150.1	149.1	Claude Opus 4.5

Agentic workLike-for-likePublic boards, shown as published, kept out of the index30

Agentic work benchmarks for Claude Opus 4.5 and DeepSeek V4 Pro 0423
Benchmark	Claude Opus 4.5	DeepSeek V4 Pro 0423	Leader
AA Agentic Index	Not measured	26.3	Only DeepSeek V4 Pro 0423 measured
Design Arena: agents building web apps	1159	1000	Claude Opus 4.5
Design Arena: agents building full-stack apps	1156	948	Claude Opus 4.5
Design Arena: agents building mobile apps	1189	Not measured	Only Claude Opus 4.5 measured
Design Arena: agents building Android apps	1175	Not measured	Only Claude Opus 4.5 measured
Design Arena: agents building Godot games	Not measured	1059	Only DeepSeek V4 Pro 0423 measured
Finance Agent (Vals AI)	Not measured	44.1%	Only DeepSeek V4 Pro 0423 measured
Tax Agent Bench (Vals AI)	Not measured	25.2%	Only DeepSeek V4 Pro 0423 measured
Legal Research Bench (Vals AI)	Not measured	23.1%	Only DeepSeek V4 Pro 0423 measured
Excel Modeling Benchmark (Vals AI)	Not measured	51.6%	Only DeepSeek V4 Pro 0423 measured
τ²-Bench Telecom	89.5%	Not measured	Only Claude Opus 4.5 measured
METR time horizons	75.0%	Not measured	Only Claude Opus 4.5 measured
Remote Labor Index	3.8%	Not measured	Only Claude Opus 4.5 measured
GDPval	45.5%	Not measured	Only Claude Opus 4.5 measured
BALROG	43.5%	Not measured	Only Claude Opus 4.5 measured
DeepResearch Bench	54.8%	Not measured	Only Claude Opus 4.5 measured
OSWorld	66.3%	Not measured	Only Claude Opus 4.5 measured
Vending-Bench 2	$4,967	$3,285	Claude Opus 4.5
Berkeley Function Calling Leaderboard (BFCL)	77.5%	Not measured	Only Claude Opus 4.5 measured
Neither model has a result on the other 22 boards here

ReasoningLike-for-likePublic boards, shown as published, kept out of the index53

Reasoning benchmarks for Claude Opus 4.5 and DeepSeek V4 Pro 0423
Benchmark	Claude Opus 4.5	DeepSeek V4 Pro 0423	Leader
GPQA Diamond	85.9%	89.4%	DeepSeek V4 Pro 0423
MMMU Pro (Vals AI)	83.0%	Not measured	Only Claude Opus 4.5 measured
GPQA Diamond (Artificial Analysis run)	86.6%	Not measured	Only Claude Opus 4.5 measured
Humanity's Last Exam (Artificial Analysis run)	30.1%	Not measured	Only Claude Opus 4.5 measured
GPQA Diamond (Epoch AI run)	86.0%	90.9%	DeepSeek V4 Pro 0423
ARC-AGI	80.0%	Not measured	Only Claude Opus 4.5 measured
ARC-AGI-2	37.6%	Not measured	Only Claude Opus 4.5 measured
SimpleBench	62.0%	Not measured	Only Claude Opus 4.5 measured
Chess puzzles	14.0%	19.0%	DeepSeek V4 Pro 0423
Mystery game puzzles	22.0%	17.0%	Claude Opus 4.5
EBR-bench	14.3%	Not measured	Only Claude Opus 4.5 measured
VPCT	40.0%	Not measured	Only Claude Opus 4.5 measured
LMArena Text: hard prompts	1476	1461	Claude Opus 4.5
LMArena Text: expert	1487	1463	Claude Opus 4.5
LMArena Text: hard prompts in English	1482	1466	Claude Opus 4.5
Kagi LLM Benchmark	80.2%	53.5%	Claude Opus 4.5
Neither model has a result on the other 6 boards here

MathLike-for-likePublic boards, shown as published, kept out of the index42

Math benchmarks for Claude Opus 4.5 and DeepSeek V4 Pro 0423
Benchmark	Claude Opus 4.5	DeepSeek V4 Pro 0423	Leader
AIME	95.4%	Not measured	Only Claude Opus 4.5 measured
MGSM (Vals AI)	95.2%	Not measured	Only Claude Opus 4.5 measured
AA Math Index	91.3	Not measured	Only Claude Opus 4.5 measured
AIME 2025 (Artificial Analysis run)	91.3%	Not measured	Only Claude Opus 4.5 measured
OTIS Mock AIME	86.1%	96.7%	DeepSeek V4 Pro 0423
FrontierMath, tiers 1 to 3	34.4%	45.3%	DeepSeek V4 Pro 0423
FrontierMath, tier 4	4.9%	2.4%	Claude Opus 4.5
ProofBench	36.0%	16.0%	Claude Opus 4.5
LMArena Text: math	1463	1443	Claude Opus 4.5
LMArena Text: mathematical work	1468	1455	Claude Opus 4.5
Neither model has a result on the other 3 boards here

KnowledgeLike-for-likePublic boards, shown as published, kept out of the index74

Knowledge benchmarks for Claude Opus 4.5 and DeepSeek V4 Pro 0423
Benchmark	Claude Opus 4.5	DeepSeek V4 Pro 0423	Leader
MMLU Pro	87.3%	87.3%	Claude Opus 4.5
LegalBench (Vals AI)	84.6%	80.3%	Claude Opus 4.5
CaseLaw (Vals AI)	62.6%	59.4%	Claude Opus 4.5
CorpFin (Vals AI)	65.1%	61.4%	Claude Opus 4.5
TaxEval (Vals AI)	74.9%	72.1%	Claude Opus 4.5
MortgageTax (Vals AI)	68.7%	Not measured	Only Claude Opus 4.5 measured
MedQA (Vals AI)	95.9%	Not measured	Only Claude Opus 4.5 measured
MedCode (Vals AI)	49.2%	40.5%	Claude Opus 4.5
MMLU Pro (Artificial Analysis run)	89.5%	Not measured	Only Claude Opus 4.5 measured
SimpleQA Verified	45.7%	47.0%	DeepSeek V4 Pro 0423
GeoBench	75.0%	Not measured	Only Claude Opus 4.5 measured
LMArena Text: science	1454	1470	DeepSeek V4 Pro 0423
LMArena Text: medicine and healthcare	1444	1466	DeepSeek V4 Pro 0423
LMArena Text: legal and government	1459	1464	DeepSeek V4 Pro 0423
LMArena Text: business and finance	1448	1443	Claude Opus 4.5
FACTS Benchmark Suite	43.9%	Not measured	Only Claude Opus 4.5 measured
Neither model has a result on the other 2 boards here

Web designLike-for-likePublic boards, shown as published, kept out of the index61

Web design benchmarks for Claude Opus 4.5 and DeepSeek V4 Pro 0423
Benchmark	Claude Opus 4.5	DeepSeek V4 Pro 0423	Leader
Design Arena: websites	1247	1234	Claude Opus 4.5
Design Arena: UI components	1238	1222	Claude Opus 4.5
Design Arena: game dev	1229	1229	Tie
Design Arena: data viz	1243	1203	Claude Opus 4.5
Design Arena: 3D	1214	1254	DeepSeek V4 Pro 0423
Design Arena: all code categories	1242	1240	Claude Opus 4.5
Design Arena: SVG	1181	1140	Claude Opus 4.5
Design Arena: ASCII art	1190	1149	Claude Opus 4.5
Neither model has a result on the other 1 board here

GeneralLike-for-likePublic boards, shown as published, kept out of the index911

General benchmarks for Claude Opus 4.5 and DeepSeek V4 Pro 0423
Benchmark	Claude Opus 4.5	DeepSeek V4 Pro 0423	Leader
Public Benefits Bench (Vals AI)	Not measured	62.9%	Only DeepSeek V4 Pro 0423 measured
SAGE (Vals AI)	52.1%	Not measured	Only Claude Opus 4.5 measured
MedScribe (Vals AI)	85.3%	75.1%	Claude Opus 4.5
IFBench	58.0%	Not measured	Only Claude Opus 4.5 measured
Long context reasoning (AA-LCR)	77.3%	Not measured	Only Claude Opus 4.5 measured
DTBench	89.9%	90.7%	DeepSeek V4 Pro 0423
LMCA	44.5%	41.2%	Claude Opus 4.5
CL-bench	21.1%	Not measured	Only Claude Opus 4.5 measured
Surface Evolver Bench	Not measured	40.0%	Only DeepSeek V4 Pro 0423 measured
Furniture assembly	28.3%	Not measured	Only Claude Opus 4.5 measured
CL-bench Life	Not measured	13.5%	Only DeepSeek V4 Pro 0423 measured
LMArena Text	1451	1451	DeepSeek V4 Pro 0423
LMArena Text: instruction following	1478	1445	Claude Opus 4.5
LMArena Text: creative writing	1445	1446	DeepSeek V4 Pro 0423
LMArena Text: English	1461	1459	Claude Opus 4.5
LMArena Text: non-English	1438	1439	DeepSeek V4 Pro 0423
LMArena Text: Chinese	1470	1481	DeepSeek V4 Pro 0423
LMArena Text: German	1449	1458	DeepSeek V4 Pro 0423
LMArena Text: Japanese	1417	1446	DeepSeek V4 Pro 0423
LMArena Text: Korean	1424	1409	Claude Opus 4.5
LMArena Text: French	1471	1473	DeepSeek V4 Pro 0423
LMArena Text: Spanish	1457	1457	Claude Opus 4.5
LMArena Text: Russian	1447	1453	DeepSeek V4 Pro 0423
LMArena Text: Polish	1439	1461	DeepSeek V4 Pro 0423
LMArena Text: multi-turn	1466	1468	DeepSeek V4 Pro 0423
LMArena Text: longer queries	1479	1458	Claude Opus 4.5
LMArena Text: writing and language	1452	1447	Claude Opus 4.5
LMArena Text: entertainment and media	1434	1431	Claude Opus 4.5
LMArena Document	1462	Not measured	Only Claude Opus 4.5 measured
Neither model has a result on the other 17 boards here

Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared

Image generation benchmarks for Claude Opus 4.5 and DeepSeek V4 Pro 0423
Benchmark	Claude Opus 4.5	DeepSeek V4 Pro 0423	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 Opus 4.5$0.018Fits in one request

DeepSeek V4 Pro 0423$0.0026Fits in one request

DeepSeek V4 Pro 0423 costs less

Repository review

50K input + 3K output tokens

Claude Opus 4.5$0.325Fits in one request

DeepSeek V4 Pro 0423$0.069Fits in one request

DeepSeek V4 Pro 0423 costs less

Agent loop

200K input + 10K output tokens

Claude Opus 4.5$1.25Exceeds the context window

DeepSeek V4 Pro 0423$0.272Fits 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 Opus 4.5 and DeepSeek V4 Pro 0423
Specification	Anthropic Claude Opus 4.5	DeepSeek V4 Pro 0423
Maker	Anthropic	DeepSeek
Weights	No public weights listed	Open weights
Released	November 24, 2025	April 24, 2026
Context window	200K	1.05M
Input $/Mtok	$5.00	$1.225
Output $/Mtok	$25.00	$2.716
Coding index	44.0	38.7
Independent measurements behind it	3	5
Cost per solved task	$1.37	$0.57
Source	OpenRouter listing	OpenRouter listing

Questions

Is Claude Opus 4.5 better than DeepSeek V4 Pro 0423 for coding?

Pick Claude Opus 4.5 for coding: it scores 44.0 on the Vibe Coding Index against 38.7 for DeepSeek V4 Pro 0423, though on 3 benchmarks against 5. Pick DeepSeek V4 Pro 0423 for output tokens 9.2x cheaper ($2.716 vs $25.00 per million) and a lower cost per solved task ($0.57 against $1.37).

Which is cheaper, Claude Opus 4.5 or DeepSeek V4 Pro 0423?

Claude Opus 4.5 costs $5.00 per million input tokens and $25.00 per million output tokens; DeepSeek V4 Pro 0423 costs $1.225 and $2.716. Per solved SWE-bench Verified task, Claude Opus 4.5 costs $1.37 and DeepSeek V4 Pro 0423 $0.57.

Which has the bigger context window, Claude Opus 4.5 or DeepSeek V4 Pro 0423?

DeepSeek V4 Pro 0423, with 1.05M tokens against 200K.

How many benchmarks is the Claude Opus 4.5 vs DeepSeek V4 Pro 0423 comparison based on?

67 benchmarks have a result for both models as of October 21, 2026. Claude Opus 4.5's coding index rests on 3 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-opus-4-5-vs-deepseek-v4-pro" title="Claude Opus 4.5 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-opus-4-5-vs-deepseek-v4-pro">LLMBenchmark.ai, Claude Opus 4.5 vs DeepSeek V4 Pro 0423</a></p>

Claude Opus 4.5 or DeepSeek V4 Pro 0423: 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