DeepSeek V4 Flash 0731 vs Hy4 flash
DeepSeek V4 Flash 0731 leads Hy4 flash on coding, 51.8 to 44.5 on the Vibe Coding Index, and Hy4 flash costs 2.0x less per output token ($0.1405 vs $0.28 per million). Updated November 22, 2026; 9 benchmarks have a result for both.
DeepSeek V4 Flash 0731 or Hy4 flash: which to pick
Pick DeepSeek V4 Flash 0731 for coding: it scores 51.8 on the Vibe Coding Index against 44.5 for Hy4 flash.
Pick Hy4 flash for output tokens 2.0x cheaper ($0.1405 vs $0.28 per million) and work measured by Vibe Code Bench (Vals AI) or Legal Research Bench (Vals AI), where it leads.
- Shared results
- 9
- DeepSeek V4 Flash 0731 only
- 47
- Hy4 flash only
- 3
- 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.
Coding
Vibe Coding Index, six public coding benchmarks
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 scores 51.8 against 44.5.
4 and 2 benchmarks behind the scores
Reasoning
GPQA Diamond
No call
Only DeepSeek V4 Flash 0731 has a GPQA Diamond result, 89.9%.
Directional only
Knowledge
MMLU Pro
No call
Only DeepSeek V4 Flash 0731 has a MMLU Pro result, 86.2%.
Directional only
Web design
Design Arena: websites
Hy4 flash
Hy4 flash leads, 1227 against 1225.
Same board, both measured
General
Vals Index
No call
Only Hy4 flash has a Vals Index result, 50.8%.
Directional only
Long documents
Listed context window
No call
Both take 1.05M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Hy4 flash
DeepSeek V4 Flash 0731 $0.0003, Hy4 flash $0.0001 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only DeepSeek V4 Flash 0731 has the number, $0.01.
Directional only
At a glance
- Coding index
- DeepSeek V4 Flash 0731 51.8 from 4 benchmarks, Hy4 flash 44.5 from 2 benchmarks.
- Widest category
- Agentic work, 6.5 points apart on average over 2 shared benchmarks.
- Widest single gap
- Legal Research Bench (Vals AI): DeepSeek V4 Flash 0731 30.3% against Hy4 flash 38.5%, 8.2 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4 Flash 0731 $0.28 against Hy4 flash $0.1405 per million output tokens, 2.0x 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.
| Category | DeepSeek V4 Flash 0731 | Bars | Hy4 flash | Ties |
|---|---|---|---|---|
| Coding | 1 | 1 | ||
| Agentic work | 1 | 1 | ||
| Web design | 0 | 5 | ||
| All shared boards | 2 | 7 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index11
| Benchmark | DeepSeek V4 Flash 0731 | Hy4 flash | Leader |
|---|---|---|---|
| LiveCodeBench (Vals AI) | 87.3% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| SWE-bench Verified (Vals AI) | 88.8% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Terminal-Bench 4 (Vals AI) | 18.7% | 15.2% | DeepSeek V4 Flash 0731 |
| Vibe Code Bench (Vals AI) | 74.7% | 74.8% | Hy4 flash |
| Code migration (Vals AI) | 38.6% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| IOI (Vals AI) | 32.7% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Terminal-Bench 2.1 (Vals AI) | 67.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| SkillsBench (Vals AI) | 50.7% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| CyberBench (Vals AI) | 72.1% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| SciCode | 50.3% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Terminal-Bench 4.0 (Artificial Analysis run) | 12.1% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| FrontierCode | 18.8% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| WeirdML | 63.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| ALE-Bench | 1306.1 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| GameBench 2 | Not measured | 50.5 | Only Hy4 flash measured |
| Neither model has a result on the other 36 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | DeepSeek V4 Flash 0731 | Hy4 flash | Leader |
|---|---|---|---|
| Epoch Capabilities Index | 154.4 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | DeepSeek V4 Flash 0731 | Hy4 flash | Leader |
|---|---|---|---|
| Finance Agent (Vals AI) | 49.5% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Tax Agent Bench (Vals AI) | 28.1% | 23.3% | DeepSeek V4 Flash 0731 |
| Legal Research Bench (Vals AI) | 30.3% | 38.5% | Hy4 flash |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 5.4% | Only Hy4 flash measured |
| Excel Modeling Benchmark (Vals AI) | 57.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| BioMysteryBench (Vals AI) | 64.4% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Terminal-Bench-Science (Vals AI) | 4.3% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Toolathlon-Verified | 70.7% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Neither model has a result on the other 36 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index10 boards, none shared
| Benchmark | DeepSeek V4 Flash 0731 | Hy4 flash | Leader |
|---|---|---|---|
| GPQA Diamond | 89.9% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| GPQA Diamond (Artificial Analysis run) | 90.8% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Humanity's Last Exam (Artificial Analysis run) | 38.6% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| GPQA Diamond (Epoch AI run) | 91.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| ARC-AGI | 89.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| ARC-AGI-2 | 61.4% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| SimpleBench | 61.1% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Chess puzzles | 32.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Mystery game puzzles | 34.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| GoBench | 1447 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Neither model has a result on the other 16 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | DeepSeek V4 Flash 0731 | Hy4 flash | Leader |
|---|---|---|---|
| OTIS Mock AIME | 94.4% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| FrontierMath, tiers 1 to 3 | 57.5% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| FrontierMath, tier 4 | 24.4% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| ProofBench | 56.0% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Neither model has a result on the other 10 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | DeepSeek V4 Flash 0731 | Hy4 flash | Leader |
|---|---|---|---|
| MMLU Pro | 86.2% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| LegalBench (Vals AI) | 77.7% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| CorpFin (Vals AI) | 61.9% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| TaxEval (Vals AI) | 70.7% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| MedCode (Vals AI) | 41.4% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| SimpleQA Verified | 33.6% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Neither model has a result on the other 15 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | DeepSeek V4 Flash 0731 | Hy4 flash | Leader |
|---|---|---|---|
| Design Arena: websites | 1225 | 1227 | Hy4 flash |
| Design Arena: UI components | 1220 | 1262 | Hy4 flash |
| Design Arena: game dev | 1181 | 1202 | Hy4 flash |
| Design Arena: data viz | 1167 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Design Arena: 3D | 1175 | 1209 | Hy4 flash |
| Design Arena: all code categories | 1211 | 1225 | Hy4 flash |
| Design Arena: SVG | 1164 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Design Arena: ASCII art | 1083 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Neither model has a result on the other 1 board here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | DeepSeek V4 Flash 0731 | Hy4 flash | Leader |
|---|---|---|---|
| Vals Index | Not measured | 50.8% | Only Hy4 flash measured |
| MedScribe (Vals AI) | 80.4% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Long context reasoning (AA-LCR) | 79.7% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| GDPval-AA | 1437 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| DTBench | 90.9% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| LMCA | 41.7% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Neither model has a result on the other 43 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V4 Flash 0731 | Hy4 flash | 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
Hy4 flash costs less
Repository review
50K input + 3K output tokens
Hy4 flash costs less
Agent loop
200K input + 10K output tokens
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.
| Specification | DeepSeek V4 Flash 0731 | Tencent Hy4 flash |
|---|---|---|
| Maker | DeepSeek | Tencent |
| Weights | Open weights | Open weights |
| Released | July 31, 2026 | November 16, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $0.13 | $0.035 |
| Output $/Mtok | $0.28 | $0.1405 |
| Coding index | 51.8 | 44.5 |
| Independent measurements behind it | 4 | 2 |
| Cost per solved task | $0.01 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4 Flash 0731 better than Hy4 flash for coding?
Pick DeepSeek V4 Flash 0731 for coding: it scores 51.8 on the Vibe Coding Index against 44.5 for Hy4 flash. Pick Hy4 flash for output tokens 2.0x cheaper ($0.1405 vs $0.28 per million) and work measured by Vibe Code Bench (Vals AI) or Legal Research Bench (Vals AI), where it leads.
Which is cheaper, DeepSeek V4 Flash 0731 or Hy4 flash?
DeepSeek V4 Flash 0731 costs $0.13 per million input tokens and $0.28 per million output tokens; Hy4 flash costs $0.035 and $0.1405. Cost per solved task is known for DeepSeek V4 Flash 0731 only.
Which has the bigger context window, DeepSeek V4 Flash 0731 or Hy4 flash?
Neither: both take 1.05M tokens.
How many benchmarks is the DeepSeek V4 Flash 0731 vs Hy4 flash comparison based on?
9 benchmarks have a result for both models as of November 22, 2026. DeepSeek V4 Flash 0731's coding index rests on 4 independent benchmarks and Hy4 flash's on 2. Where only one model has a result, the page says so instead of naming a winner.