LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Claude Opus 4.6 vs DeepSeek V4 Pro 0423

Updated October 21, 2026. 68 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Claude Opus 4.6 Replace DeepSeek V4 Pro 0423
Claude Opus 4.6Anthropic
Coding
66.9
Overall
31.9
Output $/M
$25.00
65
DeepSeek V4 Pro 0423DeepSeek
Coding
35.3
Overall
30.4
Output $/M
$1.9105
3
vs boards won of 68 shared

Decision reading

Pick Claude Opus 4.6 for coding: it scores 66.9 on the Vibe Coding Index against 35.3 for DeepSeek V4 Pro 0423.

Pick DeepSeek V4 Pro 0423 when output tokens cost 13.1x less, or when a solved task costs $0.57 against $1.56.

Model AClaude Opus 4.6Anthropic66.9/1002 independent benchmarks$1.56 per solved taskModel BDeepSeek V4 Pro 0423DeepSeek35.3/1001 independent benchmark$0.57 per solved task
Shared results
68
Claude Opus 4.6 only
40
DeepSeek V4 Pro 0423 only
15
Like-for-like categories
8 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 Opus 4.6 66.9 from 2 benchmarks, DeepSeek V4 Pro 0423 35.3 from 1 benchmark.
Widest category
Agentic work, 29.8 points apart on average over 3 shared benchmarks.
Widest single gap
Design Arena: agents building full-stack apps: Claude Opus 4.6 1220 against DeepSeek V4 Pro 0423 948, 34.0 points apart on a 0 to 100 scale.
Output price
Claude Opus 4.6 $25.00 against DeepSeek V4 Pro 0423 $1.9105 per million output tokens, 13.1x apart.
Context window
Claude Opus 4.6 takes 1M 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
CategoryClaude Opus 4.6BarsDeepSeek V4 Pro 0423Ties
Coding91
Intelligence20
Agentic work30
Reasoning61
Math51
Knowledge110
Web design80
General210
All shared boards653
CodingLike-for-likeFour of these boards feed the Vibe Coding Index91
Coding benchmarks for Claude Opus 4.6 and DeepSeek V4 Pro 0423
BenchmarkClaude Opus 4.6DeepSeek V4 Pro 0423Leader
SWE-bench Verified75.6%Not measuredOnly Claude Opus 4.6 measured
SWE-bench Multilingual72.0%Not measuredOnly Claude Opus 4.6 measured
LMArena WebDev15471447Claude Opus 4.6
AA Coding IndexNot measured59.4Only DeepSeek V4 Pro 0423 measured
LiveCodeBench (Vals AI)84.7%87.5%DeepSeek V4 Pro 0423
SWE-bench Verified (Vals AI)78.2%77.4%Claude Opus 4.6
Terminal-Bench 4 (Vals AI)Not measured11.1%Only DeepSeek V4 Pro 0423 measured
Vibe Code Bench (Vals AI)57.6%49.9%Claude Opus 4.6
Code migration (Vals AI)Not measured26.2%Only DeepSeek V4 Pro 0423 measured
ProgramBench (Vals AI)Not measured0.0%Only DeepSeek V4 Pro 0423 measured
Terminal-Bench 2.1 (Vals AI)Not measured50.2%Only DeepSeek V4 Pro 0423 measured
SkillsBench (Vals AI)Not measured51.3%Only DeepSeek V4 Pro 0423 measured
Terminal-Bench Hard (Artificial Analysis run)48.5%Not measuredOnly Claude Opus 4.6 measured
Terminal-Bench79.8%Not measuredOnly Claude Opus 4.6 measured
FrontierCode26.6%17.6%Claude Opus 4.6
GSO-Bench41.2%Not measuredOnly Claude Opus 4.6 measured
WeirdML78.0%48.9%Claude Opus 4.6
Cybench93.0%Not measuredOnly Claude Opus 4.6 measured
ALE-BenchNot measured1006.1Only DeepSeek V4 Pro 0423 measured
LMArena Text: coding15341470Claude Opus 4.6
LMArena Text: software and IT15271469Claude Opus 4.6
LMArena WebDev: React15391441Claude Opus 4.6
LMArena WebDev: HTML15591435Claude Opus 4.6
LMArena WebDev: from an image1543Not measuredOnly Claude Opus 4.6 measured
Neither model has a result on the other 14 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Claude Opus 4.6 and DeepSeek V4 Pro 0423
BenchmarkClaude Opus 4.6DeepSeek V4 Pro 0423Leader
AA Intelligence Index31.930.4Claude Opus 4.6
Epoch Capabilities Index155.7149.1Claude Opus 4.6
Agentic workLike-for-likePublic boards, shown as published, kept out of the index30
Agentic work benchmarks for Claude Opus 4.6 and DeepSeek V4 Pro 0423
BenchmarkClaude Opus 4.6DeepSeek V4 Pro 0423Leader
AA Agentic IndexNot measured26.3Only DeepSeek V4 Pro 0423 measured
Design Arena: agents building web apps12061000Claude Opus 4.6
Design Arena: agents building full-stack apps1220948Claude Opus 4.6
Design Arena: agents building mobile apps1207Not measuredOnly Claude Opus 4.6 measured
Design Arena: agents building Android apps1204Not measuredOnly Claude Opus 4.6 measured
Design Arena: agents building Godot gamesNot measured1059Only DeepSeek V4 Pro 0423 measured
Design Arena: agents building games1214Not measuredOnly Claude Opus 4.6 measured
Finance Agent (Vals AI)Not measured44.1%Only DeepSeek V4 Pro 0423 measured
Tax Agent Bench (Vals AI)Not measured25.2%Only DeepSeek V4 Pro 0423 measured
Legal Research Bench (Vals AI)Not measured23.1%Only DeepSeek V4 Pro 0423 measured
Excel Modeling Benchmark (Vals AI)Not measured51.6%Only DeepSeek V4 Pro 0423 measured
τ²-Bench Telecom92.1%Not measuredOnly Claude Opus 4.6 measured
APEX-Agents46.3%Not measuredOnly Claude Opus 4.6 measured
METR time horizons78.9%Not measuredOnly Claude Opus 4.6 measured
Remote Labor Index4.2%Not measuredOnly Claude Opus 4.6 measured
DeepResearch Bench55.3%Not measuredOnly Claude Opus 4.6 measured
Vending-Bench 2$8,018$3,285Claude Opus 4.6
Neither model has a result on the other 22 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index61
Reasoning benchmarks for Claude Opus 4.6 and DeepSeek V4 Pro 0423
BenchmarkClaude Opus 4.6DeepSeek V4 Pro 0423Leader
GPQA Diamond89.7%89.4%Claude Opus 4.6
MMMU Pro (Vals AI)83.9%Not measuredOnly Claude Opus 4.6 measured
GPQA Diamond (Artificial Analysis run)89.6%Not measuredOnly Claude Opus 4.6 measured
Humanity's Last Exam (Artificial Analysis run)39.9%Not measuredOnly Claude Opus 4.6 measured
GPQA Diamond (Epoch AI run)90.5%90.9%DeepSeek V4 Pro 0423
ARC-AGI94.0%Not measuredOnly Claude Opus 4.6 measured
ARC-AGI-269.2%Not measuredOnly Claude Opus 4.6 measured
SimpleBench67.6%Not measuredOnly Claude Opus 4.6 measured
Chess puzzles21.0%19.0%Claude Opus 4.6
Mystery game puzzles25.0%17.0%Claude Opus 4.6
EBR-bench12.7%Not measuredOnly Claude Opus 4.6 measured
LMArena Text: hard prompts15251461Claude Opus 4.6
LMArena Text: expert15441463Claude Opus 4.6
LMArena Text: hard prompts in English15301466Claude Opus 4.6
LMArena Vision: diagrams1340Not measuredOnly Claude Opus 4.6 measured
LMArena Vision: homework1337Not measuredOnly Claude Opus 4.6 measured
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index51
Math benchmarks for Claude Opus 4.6 and DeepSeek V4 Pro 0423
BenchmarkClaude Opus 4.6DeepSeek V4 Pro 0423Leader
AIME95.6%Not measuredOnly Claude Opus 4.6 measured
OTIS Mock AIME94.4%96.7%DeepSeek V4 Pro 0423
FrontierMath, tiers 1 to 366.0%45.3%Claude Opus 4.6
FrontierMath, tier 426.8%2.4%Claude Opus 4.6
ProofBench50.0%16.0%Claude Opus 4.6
LMArena Text: math15181443Claude Opus 4.6
LMArena Text: mathematical work15251455Claude Opus 4.6
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index110
Knowledge benchmarks for Claude Opus 4.6 and DeepSeek V4 Pro 0423
BenchmarkClaude Opus 4.6DeepSeek V4 Pro 0423Leader
MMLU Pro89.1%87.3%Claude Opus 4.6
LegalBench (Vals AI)85.3%80.3%Claude Opus 4.6
CaseLaw (Vals AI)62.1%59.4%Claude Opus 4.6
CorpFin (Vals AI)67.0%61.4%Claude Opus 4.6
TaxEval (Vals AI)76.0%72.1%Claude Opus 4.6
MortgageTax (Vals AI)68.5%Not measuredOnly Claude Opus 4.6 measured
MedQA (Vals AI)95.4%Not measuredOnly Claude Opus 4.6 measured
MedCode (Vals AI)49.1%40.5%Claude Opus 4.6
SimpleQA Verified47.0%47.0%Claude Opus 4.6
LMArena Text: science15191470Claude Opus 4.6
LMArena Text: medicine and healthcare15041466Claude Opus 4.6
LMArena Text: legal and government15121464Claude Opus 4.6
LMArena Text: business and finance14971443Claude Opus 4.6
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for Claude Opus 4.6 and DeepSeek V4 Pro 0423
BenchmarkClaude Opus 4.6DeepSeek V4 Pro 0423Leader
Design Arena: websites12911235Claude Opus 4.6
Design Arena: UI components12841221Claude Opus 4.6
Design Arena: game dev12781229Claude Opus 4.6
Design Arena: data viz12791203Claude Opus 4.6
Design Arena: 3D12741254Claude Opus 4.6
Design Arena: all code categories12891240Claude Opus 4.6
Design Arena: SVG12271139Claude Opus 4.6
Design Arena: ASCII art12541148Claude Opus 4.6
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index210
General benchmarks for Claude Opus 4.6 and DeepSeek V4 Pro 0423
BenchmarkClaude Opus 4.6DeepSeek V4 Pro 0423Leader
Public Benefits Bench (Vals AI)Not measured62.9%Only DeepSeek V4 Pro 0423 measured
SAGE (Vals AI)51.6%Not measuredOnly Claude Opus 4.6 measured
MedScribe (Vals AI)86.7%75.1%Claude Opus 4.6
IFBench53.1%Not measuredOnly Claude Opus 4.6 measured
Long context reasoning (AA-LCR)78.0%Not measuredOnly Claude Opus 4.6 measured
DTBench91.2%90.7%Claude Opus 4.6
LMCA55.8%41.2%Claude Opus 4.6
CL-bench20.7%Not measuredOnly Claude Opus 4.6 measured
Surface Evolver BenchNot measured40.0%Only DeepSeek V4 Pro 0423 measured
Furniture assembly28.3%Not measuredOnly Claude Opus 4.6 measured
CL-bench Life17.0%13.5%Claude Opus 4.6
LMArena Text15011451Claude Opus 4.6
LMArena Text: instruction following15211445Claude Opus 4.6
LMArena Text: creative writing15051446Claude Opus 4.6
LMArena Vision1316Not measuredOnly Claude Opus 4.6 measured
LMArena Text: English15111459Claude Opus 4.6
LMArena Text: non-English14881439Claude Opus 4.6
LMArena Text: Chinese15511481Claude Opus 4.6
LMArena Text: German15001458Claude Opus 4.6
LMArena Text: Japanese14881446Claude Opus 4.6
LMArena Text: Korean14641409Claude Opus 4.6
LMArena Text: French15121473Claude Opus 4.6
LMArena Text: Spanish15101457Claude Opus 4.6
LMArena Text: Russian14971453Claude Opus 4.6
LMArena Text: Polish14991461Claude Opus 4.6
LMArena Text: multi-turn15111468Claude Opus 4.6
LMArena Text: longer queries15181458Claude Opus 4.6
LMArena Text: writing and language15021447Claude Opus 4.6
LMArena Text: entertainment and media14921431Claude Opus 4.6
LMArena Vision: English1324Not measuredOnly Claude Opus 4.6 measured
LMArena Vision: Chinese1370Not measuredOnly Claude Opus 4.6 measured
LMArena Vision: reading text1326Not measuredOnly Claude Opus 4.6 measured
LMArena Vision: humor1314Not measuredOnly Claude Opus 4.6 measured
LMArena Vision: recognizing things1274Not measuredOnly Claude Opus 4.6 measured
LMArena Vision: creative writing1331Not measuredOnly Claude Opus 4.6 measured
LMArena Document1507Not measuredOnly Claude Opus 4.6 measured
Neither model has a result on the other 10 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Claude Opus 4.6 and DeepSeek V4 Pro 0423
BenchmarkClaude Opus 4.6DeepSeek V4 Pro 0423Leader
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 4.6$0.018Fits in one request
DeepSeek V4 Pro 0423$0.0019Fits in one request

DeepSeek V4 Pro 0423 costs less

Repository review

50K input + 3K output tokens

Claude Opus 4.6$0.325Fits in one request
DeepSeek V4 Pro 0423$0.053Fits in one request

DeepSeek V4 Pro 0423 costs less

Agent loop

200K input + 10K output tokens

Claude Opus 4.6$1.25Fits in one request
DeepSeek V4 Pro 0423$0.210Fits 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 4.6 and DeepSeek V4 Pro 0423
SpecificationAnthropic Claude Opus 4.6DeepSeek V4 Pro 0423
MakerAnthropicDeepSeek
WeightsNo public weights listedOpen weights
ReleasedFebruary 4, 2026April 24, 2026
Context window1M1.05M
Input $/Mtok$5.00$0.9553
Output $/Mtok$25.00$1.9105
Coding index66.935.3
Independent measurements behind it21
Cost per solved task$1.56$0.57
SourceOpenRouter listingOpenRouter listing

Questions

Is Claude Opus 4.6 better than DeepSeek V4 Pro 0423 for coding?

Pick Claude Opus 4.6 for coding: it scores 66.9 on the Vibe Coding Index against 35.3 for DeepSeek V4 Pro 0423. Pick DeepSeek V4 Pro 0423 when output tokens cost 13.1x less, or when a solved task costs $0.57 against $1.56.

Which is cheaper, Claude Opus 4.6 or DeepSeek V4 Pro 0423?

Claude Opus 4.6 costs $5.00 per million input tokens and $25.00 per million output tokens; DeepSeek V4 Pro 0423 costs $0.9553 and $1.9105. Per solved SWE-bench Verified task, Claude Opus 4.6 costs $1.56 and DeepSeek V4 Pro 0423 $0.57.

Which has the bigger context window, Claude Opus 4.6 or DeepSeek V4 Pro 0423?

DeepSeek V4 Pro 0423, with 1.05M tokens against 1M.

How many benchmarks is the Claude Opus 4.6 vs DeepSeek V4 Pro 0423 comparison based on?

68 benchmarks have a result for both models as of October 21, 2026. Claude Opus 4.6's coding index rests on 2 independent benchmarks and DeepSeek V4 Pro 0423's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next