Enter opens the highlighted result. Esc closes.

DeepSeek V4 Pro 0423 vs Inkling

DeepSeek V4 Pro 0423 leads Inkling on coding, 38.7 to 31.5 on the Vibe Coding Index, and DeepSeek V4 Pro 0423 costs 1.4x less per output token ($2.976 vs $4.05 per million). Updated October 22, 2026; 76 benchmarks have a result for both.

Replace DeepSeek V4 Pro 0423 Replace Inkling
DeepSeek V4 Pro 0423DeepSeek
Coding
38.7
Overall
50.0
Output $/M
$2.976
60
T InklingThinking Machines
Coding
31.5
Overall
46.5
Output $/M
$4.05
15
vs boards won of 76 shared, 1 tied

DeepSeek V4 Pro 0423 or Inkling: which to pick

Pick DeepSeek V4 Pro 0423 for coding: it scores 38.7 on the Vibe Coding Index against 31.5 for Inkling, though on 5 benchmarks against 6.

Pick Inkling for work measured by SWE-bench Verified (Vals AI) or Design Arena: agents building web apps, where it leads.

Model ADeepSeek V4 Pro 0423DeepSeek38.7/1005 independent benchmarks$0.57 per solved taskModel BInklingThinking Machines31.5/1006 independent benchmarks$0.76 per solved task
Shared results
76
DeepSeek V4 Pro 0423 only
8
Inkling only
26
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.

At a glance

Coding index
DeepSeek V4 Pro 0423 38.7 from 5 benchmarks, Inkling 31.5 from 6 benchmarks.
Widest category
Agentic work, 9.9 points apart on average over 6 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): DeepSeek V4 Pro 0423 49.9% against Inkling 19.2%, 30.7 points apart on a 0 to 100 scale.
Output price
DeepSeek V4 Pro 0423 $2.976 against Inkling $4.05 per million output tokens, 1.4x apart.
Context window
DeepSeek V4 Pro 0423 takes 1.05M tokens, Inkling 524K.

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
CategoryDeepSeek V4 Pro 0423BarsInklingTies
Coding1511 tie
Intelligence20
Agentic work33
Reasoning42
Math33
Knowledge64
Web design80
General192
All shared boards60151 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index151
Coding benchmarks for DeepSeek V4 Pro 0423 and Inkling
BenchmarkDeepSeek V4 Pro 0423InklingLeader
LiveBench codingNot measured64.0%Only Inkling measured
LMArena WebDev14471414DeepSeek V4 Pro 0423
AA Coding Index59.452.1DeepSeek V4 Pro 0423
LiveCodeBench (Vals AI)87.5%85.5%DeepSeek V4 Pro 0423
SWE-bench Verified (Vals AI)77.4%77.6%Inkling
Terminal-Bench 4 (Vals AI)11.1%0.5%DeepSeek V4 Pro 0423
Vibe Code Bench (Vals AI)49.9%19.2%DeepSeek V4 Pro 0423
Code migration (Vals AI)26.2%11.8%DeepSeek V4 Pro 0423
ProgramBench (Vals AI)0.0%0.0%Tie
IOI (Vals AI)Not measured14.9%Only Inkling measured
Terminal-Bench 2.1 (Vals AI)50.2%47.6%DeepSeek V4 Pro 0423
Vibe Code Bench 1-100 (Vals AI)Not measured7.3%Only Inkling measured
SkillsBench (Vals AI)51.3%26.1%DeepSeek V4 Pro 0423
CyberBench (Vals AI)Not measured66.8%Only Inkling measured
SciCodeNot measured47.0%Only Inkling measured
FrontierCode17.6%14.0%DeepSeek V4 Pro 0423
FrontierSWENot measured4.1%Only Inkling measured
WeirdML48.9%32.3%DeepSeek V4 Pro 0423
ALE-Bench1006.1946.0DeepSeek V4 Pro 0423
LMArena Text: coding14701466DeepSeek V4 Pro 0423
LMArena Text: software and IT14691465DeepSeek V4 Pro 0423
LMArena WebDev: React14411404DeepSeek V4 Pro 0423
LMArena WebDev: HTML14351399DeepSeek V4 Pro 0423
Neither model has a result on the other 16 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for DeepSeek V4 Pro 0423 and Inkling
BenchmarkDeepSeek V4 Pro 0423InklingLeader
AA Intelligence Index30.425.0DeepSeek V4 Pro 0423
Epoch Capabilities Index149.1148.4DeepSeek V4 Pro 0423
Agentic workLike-for-likePublic boards, shown as published, kept out of the index33
Agentic work benchmarks for DeepSeek V4 Pro 0423 and Inkling
BenchmarkDeepSeek V4 Pro 0423InklingLeader
AA Agentic Index26.322.5DeepSeek V4 Pro 0423
Design Arena: agents building web apps10001196Inkling
Design Arena: agents building full-stack apps948Not measuredOnly DeepSeek V4 Pro 0423 measured
Design Arena: agents building Godot games1059Not measuredOnly DeepSeek V4 Pro 0423 measured
LiveBench researchNot measured59.9%Only Inkling measured
LiveBench browserNot measured16.0%Only Inkling measured
LiveBench long agenticNot measured14.1%Only Inkling measured
SREBench (Vals AI)Not measured0.0%Only Inkling measured
Finance Agent (Vals AI)44.1%46.6%Inkling
Tax Agent Bench (Vals AI)25.2%15.3%DeepSeek V4 Pro 0423
Legal Research Bench (Vals AI)23.1%28.4%Inkling
Harvey's Legal Agent Benchmark (Vals AI)Not measured3.8%Only Inkling measured
Excel Modeling Benchmark (Vals AI)51.6%38.4%DeepSeek V4 Pro 0423
APEX-AgentsNot measured33.8%Only Inkling measured
Vending-Bench 2$3,285Not measuredOnly DeepSeek V4 Pro 0423 measured
Neither model has a result on the other 26 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index42
Reasoning benchmarks for DeepSeek V4 Pro 0423 and Inkling
BenchmarkDeepSeek V4 Pro 0423InklingLeader
GPQA Diamond89.4%87.1%DeepSeek V4 Pro 0423
LiveBench reasoningNot measured78.3%Only Inkling measured
MMMU Pro (Vals AI)Not measured78.5%Only Inkling measured
GPQA Diamond (Artificial Analysis run)Not measured87.2%Only Inkling measured
Humanity's Last Exam (Artificial Analysis run)Not measured31.9%Only Inkling measured
GPQA Diamond (Epoch AI run)90.9%88.3%DeepSeek V4 Pro 0423
ARC-AGINot measured79.5%Only Inkling measured
ARC-AGI-2Not measured36.5%Only Inkling measured
SimpleBenchNot measured50.0%Only Inkling measured
Chess puzzles19.0%21.0%Inkling
Mystery game puzzles17.0%Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: hard prompts14611451DeepSeek V4 Pro 0423
LMArena Text: expert14631466Inkling
LMArena Text: hard prompts in English14661448DeepSeek V4 Pro 0423
Kagi LLM Benchmark53.5%Not measuredOnly DeepSeek V4 Pro 0423 measured
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index33
Math benchmarks for DeepSeek V4 Pro 0423 and Inkling
BenchmarkDeepSeek V4 Pro 0423InklingLeader
OTIS Mock AIME96.7%88.9%DeepSeek V4 Pro 0423
FrontierMath, tiers 1 to 345.3%33.3%DeepSeek V4 Pro 0423
FrontierMath, tier 42.4%4.9%Inkling
ProofBench16.0%0.0%DeepSeek V4 Pro 0423
LMArena Text: math14431479Inkling
LMArena Text: mathematical work14551460Inkling
Neither model has a result on the other 7 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index64
Knowledge benchmarks for DeepSeek V4 Pro 0423 and Inkling
BenchmarkDeepSeek V4 Pro 0423InklingLeader
MMLU Pro87.3%86.3%DeepSeek V4 Pro 0423
LegalBench (Vals AI)80.3%83.0%Inkling
CaseLaw (Vals AI)59.4%Not measuredOnly DeepSeek V4 Pro 0423 measured
CorpFin (Vals AI)61.4%68.6%Inkling
TaxEval (Vals AI)72.1%75.3%Inkling
MortgageTax (Vals AI)Not measured64.0%Only Inkling measured
MedCode (Vals AI)40.5%41.2%Inkling
SimpleQA Verified47.0%40.3%DeepSeek V4 Pro 0423
LMArena Text: science14701455DeepSeek V4 Pro 0423
LMArena Text: medicine and healthcare14661447DeepSeek V4 Pro 0423
LMArena Text: legal and government14641448DeepSeek V4 Pro 0423
LMArena Text: business and finance14431438DeepSeek V4 Pro 0423
Neither model has a result on the other 6 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for DeepSeek V4 Pro 0423 and Inkling
BenchmarkDeepSeek V4 Pro 0423InklingLeader
Design Arena: websites12341224DeepSeek V4 Pro 0423
Design Arena: UI components12191198DeepSeek V4 Pro 0423
Design Arena: game dev12281165DeepSeek V4 Pro 0423
Design Arena: data viz12031156DeepSeek V4 Pro 0423
Design Arena: 3D12531160DeepSeek V4 Pro 0423
Design Arena: all code categories12401205DeepSeek V4 Pro 0423
Design Arena: SVG11391108DeepSeek V4 Pro 0423
Design Arena: ASCII art11491089DeepSeek V4 Pro 0423
LiveBench designNot measured58.3%Only Inkling measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index192
General benchmarks for DeepSeek V4 Pro 0423 and Inkling
BenchmarkDeepSeek V4 Pro 0423InklingLeader
Vals IndexNot measured29.0%Only Inkling measured
LiveBench data analysisNot measured72.8%Only Inkling measured
Public Benefits Bench (Vals AI)62.9%58.5%DeepSeek V4 Pro 0423
SAGE (Vals AI)Not measured36.5%Only Inkling measured
MedScribe (Vals AI)75.1%85.4%Inkling
Vals Multimodal IndexNot measured49.4%Only Inkling measured
Long context reasoning (AA-LCR)Not measured77.3%Only Inkling measured
DTBench90.7%87.5%DeepSeek V4 Pro 0423
LMCA41.2%37.6%DeepSeek V4 Pro 0423
Surface Evolver Bench40.0%Not measuredOnly DeepSeek V4 Pro 0423 measured
CL-bench Life13.5%Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text14511442DeepSeek V4 Pro 0423
LMArena Text: instruction following14451425DeepSeek V4 Pro 0423
LMArena Text: creative writing14461390DeepSeek V4 Pro 0423
LMArena Text: English14591442DeepSeek V4 Pro 0423
LMArena Text: non-English14391434DeepSeek V4 Pro 0423
LMArena Text: Chinese14811493Inkling
LMArena Text: German14581445DeepSeek V4 Pro 0423
LMArena Text: Japanese14461429DeepSeek V4 Pro 0423
LMArena Text: Korean14091403DeepSeek V4 Pro 0423
LMArena Text: French14731455DeepSeek V4 Pro 0423
LMArena Text: Spanish14571449DeepSeek V4 Pro 0423
LMArena Text: Russian14531430DeepSeek V4 Pro 0423
LMArena Text: Polish14611450DeepSeek V4 Pro 0423
LMArena Text: multi-turn14681437DeepSeek V4 Pro 0423
LMArena Text: longer queries14581435DeepSeek V4 Pro 0423
LMArena Text: writing and language14471404DeepSeek V4 Pro 0423
LMArena Text: entertainment and media14311394DeepSeek V4 Pro 0423
Neither model has a result on the other 18 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for DeepSeek V4 Pro 0423 and Inkling
BenchmarkDeepSeek V4 Pro 0423InklingLeader
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

DeepSeek V4 Pro 0423$0.0028Fits in one request
Inkling$0.0030Fits in one request

DeepSeek V4 Pro 0423 costs less

Repository review

50K input + 3K output tokens

DeepSeek V4 Pro 0423$0.077Fits in one request
Inkling$0.061Fits in one request

Inkling costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4 Pro 0423$0.301Fits in one request
Inkling$0.235Fits in one request

Inkling 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 DeepSeek V4 Pro 0423 and Inkling
SpecificationDeepSeek V4 Pro 0423Thinking Machines Inkling
MakerDeepSeekThinking Machines
WeightsOpen weightsOpen weights
ReleasedApril 24, 2026July 17, 2026
Context window1.05M524K
Input $/Mtok$1.358$0.975
Output $/Mtok$2.976$4.05
Coding index38.731.5
Independent measurements behind it56
Cost per solved task$0.57$0.76
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V4 Pro 0423 better than Inkling for coding?

Pick DeepSeek V4 Pro 0423 for coding: it scores 38.7 on the Vibe Coding Index against 31.5 for Inkling, though on 5 benchmarks against 6. Pick Inkling for work measured by SWE-bench Verified (Vals AI) or Design Arena: agents building web apps, where it leads.

Which is cheaper, DeepSeek V4 Pro 0423 or Inkling?

DeepSeek V4 Pro 0423 costs $1.358 per million input tokens and $2.976 per million output tokens; Inkling costs $0.975 and $4.05. Per solved SWE-bench Verified task, DeepSeek V4 Pro 0423 costs $0.57 and Inkling $0.76.

Which has the bigger context window, DeepSeek V4 Pro 0423 or Inkling?

DeepSeek V4 Pro 0423, with 1.05M tokens against 524K.

How many benchmarks is the DeepSeek V4 Pro 0423 vs Inkling comparison based on?

76 benchmarks have a result for both models as of October 22, 2026. DeepSeek V4 Pro 0423's coding index rests on 5 independent benchmarks and Inkling's on 6. 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/deepseek-v4-pro-vs-thinkingmachines-inkling" title="DeepSeek V4 Pro 0423 vs Inkling, 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/deepseek-v4-pro-vs-thinkingmachines-inkling">LLMBenchmark.ai, DeepSeek V4 Pro 0423 vs Inkling</a></p>