Enter opens the highlighted result. Esc closes.

DeepSeek V4 Pro 0423 vs Hy4 flash

Hy4 flash leads DeepSeek V4 Pro 0423 on coding, 44.5 to 38.7 on the Vibe Coding Index, and Hy4 flash costs 18.2x less per output token ($0.1405 vs $2.56 per million). Updated November 22, 2026; 10 benchmarks have a result for both.

DeepSeek V4 Pro 0423DeepSeek
Coding
38.7
Overall
52.4
Output $/M
$2.56
4
Hy4 flashTencent
Coding
44.5
Overall
No data
Output $/M
$0.1405
6
vs boards won of 10 shared

DeepSeek V4 Pro 0423 or Hy4 flash: which to pick

Pick Hy4 flash for coding: it scores 44.5 on the Vibe Coding Index against 38.7 for DeepSeek V4 Pro 0423, though on 2 benchmarks against 5.

Pick DeepSeek V4 Pro 0423 for work measured by GameBench 2 or Tax Agent Bench (Vals AI), where it leads.

Shared results
10
DeepSeek V4 Pro 0423 only
79
Hy4 flash only
2
Like-for-like categories
3 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, Hy4 flash 44.5 from 2 benchmarks.
Widest category
Coding, 10.3 points apart on average over 3 shared benchmarks.
Widest single gap
Vibe Code Bench (Vals AI): DeepSeek V4 Pro 0423 49.9% against Hy4 flash 74.8%, 24.9 points apart on a 0 to 100 scale.
Output price
DeepSeek V4 Pro 0423 $2.56 against Hy4 flash $0.1405 per million output tokens, 18.2x apart.
Context window
Both take 1.05M tokens.

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 0423BarsHy4 flashTies
Coding12
Agentic work11
Web design23
All shared boards46
CodingLike-for-likeSix of these boards feed the Vibe Coding Index12
Coding benchmarks for DeepSeek V4 Pro 0423 and Hy4 flash
BenchmarkDeepSeek V4 Pro 0423Hy4 flashLeader
LMArena WebDev1448Not measuredOnly DeepSeek V4 Pro 0423 measured
LiveCodeBench (Vals AI)87.5%Not measuredOnly DeepSeek V4 Pro 0423 measured
SWE-bench Verified (Vals AI)77.4%Not measuredOnly DeepSeek V4 Pro 0423 measured
Terminal-Bench 4 (Vals AI)11.1%15.2%Hy4 flash
Vibe Code Bench (Vals AI)49.9%74.8%Hy4 flash
Code migration (Vals AI)26.2%Not measuredOnly DeepSeek V4 Pro 0423 measured
ProgramBench (Vals AI)0.0%Not measuredOnly DeepSeek V4 Pro 0423 measured
Terminal-Bench 2.1 (Vals AI)50.2%Not measuredOnly DeepSeek V4 Pro 0423 measured
SkillsBench (Vals AI)51.3%Not measuredOnly DeepSeek V4 Pro 0423 measured
FrontierCode17.6%Not measuredOnly DeepSeek V4 Pro 0423 measured
WeirdML48.6%Not measuredOnly DeepSeek V4 Pro 0423 measured
ALE-Bench1006.1Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: coding1469Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: software and IT1469Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena WebDev: React1441Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena WebDev: HTML1435Not measuredOnly DeepSeek V4 Pro 0423 measured
SWE Atlas: Codebase QnA27.2%Not measuredOnly DeepSeek V4 Pro 0423 measured
SWE Atlas: Test Writing27.1%Not measuredOnly DeepSeek V4 Pro 0423 measured
GameBench 251.350.5DeepSeek V4 Pro 0423
Neither model has a result on the other 33 boards here
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
Intelligence benchmarks for DeepSeek V4 Pro 0423 and Hy4 flash
BenchmarkDeepSeek V4 Pro 0423Hy4 flashLeader
AA Intelligence Index20.8Not measuredOnly DeepSeek V4 Pro 0423 measured
Epoch Capabilities Index150.2Not measuredOnly DeepSeek V4 Pro 0423 measured
Agentic workLike-for-likePublic boards, shown as published, kept out of the index11
Agentic work benchmarks for DeepSeek V4 Pro 0423 and Hy4 flash
BenchmarkDeepSeek V4 Pro 0423Hy4 flashLeader
Design Arena: agents building web apps1000Not measuredOnly DeepSeek V4 Pro 0423 measured
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
Finance Agent (Vals AI)44.1%Not measuredOnly DeepSeek V4 Pro 0423 measured
Tax Agent Bench (Vals AI)25.2%23.3%DeepSeek V4 Pro 0423
Legal Research Bench (Vals AI)23.1%38.5%Hy4 flash
Harvey's Legal Agent Benchmark (Vals AI)Not measured5.4%Only Hy4 flash measured
Excel Modeling Benchmark (Vals AI)51.6%Not measuredOnly DeepSeek V4 Pro 0423 measured
Vending-Bench 2$3,285Not measuredOnly DeepSeek V4 Pro 0423 measured
Toolathlon-Verified55.9%Not measuredOnly DeepSeek V4 Pro 0423 measured
Neither model has a result on the other 34 boards here
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
Reasoning benchmarks for DeepSeek V4 Pro 0423 and Hy4 flash
BenchmarkDeepSeek V4 Pro 0423Hy4 flashLeader
GPQA Diamond89.4%Not measuredOnly DeepSeek V4 Pro 0423 measured
GPQA Diamond (Epoch AI run)90.9%Not measuredOnly DeepSeek V4 Pro 0423 measured
Chess puzzles19.0%Not measuredOnly DeepSeek V4 Pro 0423 measured
Mystery game puzzles17.0%Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: hard prompts1461Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: expert1463Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: hard prompts in English1467Not measuredOnly DeepSeek V4 Pro 0423 measured
Kagi LLM Benchmark53.5%Not measuredOnly DeepSeek V4 Pro 0423 measured
Humanity's Last Exam (Scale run)13.4%Not measuredOnly DeepSeek V4 Pro 0423 measured
Neither model has a result on the other 17 boards here
MathDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Math benchmarks for DeepSeek V4 Pro 0423 and Hy4 flash
BenchmarkDeepSeek V4 Pro 0423Hy4 flashLeader
OTIS Mock AIME96.7%Not measuredOnly DeepSeek V4 Pro 0423 measured
FrontierMath, tiers 1 to 345.3%Not measuredOnly DeepSeek V4 Pro 0423 measured
FrontierMath, tier 42.4%Not measuredOnly DeepSeek V4 Pro 0423 measured
ProofBench16.0%Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: math1441Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: mathematical work1455Not measuredOnly DeepSeek V4 Pro 0423 measured
MathArena23.5%Not measuredOnly DeepSeek V4 Pro 0423 measured
Neither model has a result on the other 7 boards here
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index11 boards, none shared
Knowledge benchmarks for DeepSeek V4 Pro 0423 and Hy4 flash
BenchmarkDeepSeek V4 Pro 0423Hy4 flashLeader
MMLU Pro87.3%Not measuredOnly DeepSeek V4 Pro 0423 measured
LegalBench (Vals AI)80.3%Not measuredOnly DeepSeek V4 Pro 0423 measured
CaseLaw (Vals AI)59.4%Not measuredOnly DeepSeek V4 Pro 0423 measured
CorpFin (Vals AI)61.4%Not measuredOnly DeepSeek V4 Pro 0423 measured
TaxEval (Vals AI)72.1%Not measuredOnly DeepSeek V4 Pro 0423 measured
MedCode (Vals AI)40.5%Not measuredOnly DeepSeek V4 Pro 0423 measured
SimpleQA Verified47.0%Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: science1468Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: medicine and healthcare1464Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: legal and government1464Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: business and finance1443Not measuredOnly DeepSeek V4 Pro 0423 measured
Neither model has a result on the other 10 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index23
Web design benchmarks for DeepSeek V4 Pro 0423 and Hy4 flash
BenchmarkDeepSeek V4 Pro 0423Hy4 flashLeader
Design Arena: websites12221227Hy4 flash
Design Arena: UI components12051262Hy4 flash
Design Arena: game dev12041202DeepSeek V4 Pro 0423
Design Arena: data viz1197Not measuredOnly DeepSeek V4 Pro 0423 measured
Design Arena: 3D12201209DeepSeek V4 Pro 0423
Design Arena: all code categories12231225Hy4 flash
Design Arena: SVG1123Not measuredOnly DeepSeek V4 Pro 0423 measured
Design Arena: ASCII art1134Not measuredOnly DeepSeek V4 Pro 0423 measured
Neither model has a result on the other 1 board here
GeneralDirectional onlyPublic boards, shown as published, kept out of the index25 boards, none shared
General benchmarks for DeepSeek V4 Pro 0423 and Hy4 flash
BenchmarkDeepSeek V4 Pro 0423Hy4 flashLeader
Vals IndexNot measured50.8%Only Hy4 flash measured
Public Benefits Bench (Vals AI)62.9%Not measuredOnly DeepSeek V4 Pro 0423 measured
MedScribe (Vals AI)75.1%Not measuredOnly DeepSeek V4 Pro 0423 measured
DTBench90.7%Not measuredOnly DeepSeek V4 Pro 0423 measured
LMCA41.2%Not measuredOnly DeepSeek V4 Pro 0423 measured
Surface Evolver Bench40.0%Not measuredOnly DeepSeek V4 Pro 0423 measured
CL-bench Life13.5%Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text1451Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: instruction following1446Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: creative writing1446Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: English1460Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: non-English1439Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: Chinese1481Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: German1457Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: Japanese1444Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: Korean1407Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: French1471Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: Spanish1456Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: Russian1453Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: Polish1459Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: multi-turn1467Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: longer queries1458Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: writing and language1447Not measuredOnly DeepSeek V4 Pro 0423 measured
LMArena Text: entertainment and media1431Not measuredOnly DeepSeek V4 Pro 0423 measured
EQ-Bench 41156Not measuredOnly DeepSeek V4 Pro 0423 measured
Neither model has a result on the other 24 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 Hy4 flash
BenchmarkDeepSeek V4 Pro 0423Hy4 flashLeader
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$0.0026Fits in one request
Hy4 flash$0.0001Fits in one request

Hy4 flash costs less

Repository review

50K input + 3K output tokens

DeepSeek V4 Pro 0423$0.072Fits in one request
Hy4 flash$0.0022Fits in one request

Hy4 flash costs less

Agent loop

200K input + 10K output tokens

DeepSeek V4 Pro 0423$0.282Fits in one request
Hy4 flash$0.0084Fits in one request

Hy4 flash 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 Hy4 flash
SpecificationDeepSeek V4 Pro 0423Tencent Hy4 flash
MakerDeepSeekTencent
WeightsOpen weightsOpen weights
ReleasedApril 24, 2026November 16, 2026
Context window1.05M1.05M
Input $/Mtok$1.28$0.035
Output $/Mtok$2.56$0.1405
Coding index38.744.5
Independent measurements behind it52
Cost per solved task$0.57Not computable
SourceOpenRouter listingOpenRouter listing

Questions

Is DeepSeek V4 Pro 0423 better than Hy4 flash for coding?

Pick Hy4 flash for coding: it scores 44.5 on the Vibe Coding Index against 38.7 for DeepSeek V4 Pro 0423, though on 2 benchmarks against 5. Pick DeepSeek V4 Pro 0423 for work measured by GameBench 2 or Tax Agent Bench (Vals AI), where it leads.

Which is cheaper, DeepSeek V4 Pro 0423 or Hy4 flash?

DeepSeek V4 Pro 0423 costs $1.28 per million input tokens and $2.56 per million output tokens; Hy4 flash costs $0.035 and $0.1405. Cost per solved task is known for DeepSeek V4 Pro 0423 only.

Which has the bigger context window, DeepSeek V4 Pro 0423 or Hy4 flash?

Neither: both take 1.05M tokens.

How many benchmarks is the DeepSeek V4 Pro 0423 vs Hy4 flash comparison based on?

10 benchmarks have a result for both models as of November 22, 2026. DeepSeek V4 Pro 0423's coding index rests on 5 independent benchmarks and Hy4 flash's on 2. 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-tencent-hy4-flash" title="DeepSeek V4 Pro 0423 vs Hy4 flash, 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-tencent-hy4-flash">LLMBenchmark.ai, DeepSeek V4 Pro 0423 vs Hy4 flash</a></p>