DeepSeek V4 Flash 0731 vs Hy4
Hy4 leads DeepSeek V4 Flash 0731 on coding, 65.2 to 51.8 on the Vibe Coding Index, and DeepSeek V4 Flash 0731 costs 4.2x less per output token ($0.30 vs $1.2505 per million). Updated November 5, 2026; 4 benchmarks have a result for both.
DeepSeek V4 Flash 0731 or Hy4: which to pick
Pick Hy4 for coding: it scores 65.2 on the Vibe Coding Index against 51.8 for DeepSeek V4 Flash 0731, though on 2 benchmarks against 4.
Pick DeepSeek V4 Flash 0731 for output tokens 4.2x cheaper ($0.30 vs $1.2505 per million).
- Shared results
- 4
- DeepSeek V4 Flash 0731 only
- 52
- Hy4 only
- 2
- Like-for-like categories
- 2 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
Hy4
Hy4 scores 65.2 against 51.8.
4 and 2 benchmarks behind the scores
Agentic work
AA Agentic Index
No call
Only DeepSeek V4 Flash 0731 has a AA Agentic Index result, 41.0.
Directional only
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
No call
Only DeepSeek V4 Flash 0731 has a Design Arena: websites result, 1236.
Directional only
General
Vals Index
No call
Only Hy4 has a Vals Index result, 59.4%.
Directional only
Long documents
Listed context window
No call
Both take 1.05M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 $0.0003, Hy4 $0.0010 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 65.2 from 2 benchmarks.
- Widest category
- Coding, 16.9 points apart on average over 2 shared benchmarks.
- Widest single gap
- Terminal-Bench 4 (Vals AI): DeepSeek V4 Flash 0731 18.7% against Hy4 39.4%, 27.6 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4 Flash 0731 $0.30 against Hy4 $1.2505 per million output tokens, 4.2x 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.
| Category | DeepSeek V4 Flash 0731 | Bars | Hy4 | Ties |
|---|---|---|---|---|
| Coding | 0 | 2 | ||
| Agentic work | 0 | 2 | ||
| All shared boards | 0 | 4 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index02
| Benchmark | DeepSeek V4 Flash 0731 | Hy4 | Leader |
|---|---|---|---|
| AA Coding Index | 69.1 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| 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% | 39.4% | Hy4 |
| Vibe Code Bench (Vals AI) | 74.7% | 81.0% | Hy4 |
| 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 |
| 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 |
| Neither model has a result on the other 35 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | DeepSeek V4 Flash 0731 | Hy4 | Leader |
|---|---|---|---|
| Epoch Capabilities Index | 154.3 | 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 index02
| Benchmark | DeepSeek V4 Flash 0731 | Hy4 | Leader |
|---|---|---|---|
| AA Agentic Index | 41.0 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Finance Agent (Vals AI) | 49.5% | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Tax Agent Bench (Vals AI) | 28.1% | 34.4% | Hy4 |
| Legal Research Bench (Vals AI) | 30.3% | 41.4% | Hy4 |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 12.5% | Only Hy4 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 35 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index10 boards, none shared
| Benchmark | DeepSeek V4 Flash 0731 | Hy4 | 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 | 1449 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Neither model has a result on the other 14 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | DeepSeek V4 Flash 0731 | Hy4 | 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 | 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 14 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | DeepSeek V4 Flash 0731 | Hy4 | Leader |
|---|---|---|---|
| Design Arena: websites | 1236 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Design Arena: UI components | 1230 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Design Arena: game dev | 1207 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Design Arena: data viz | 1180 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Design Arena: 3D | 1206 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Design Arena: all code categories | 1228 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Design Arena: SVG | 1179 | Not measured | Only DeepSeek V4 Flash 0731 measured |
| Design Arena: ASCII art | 1087 | 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 index5 boards, none shared
| Benchmark | DeepSeek V4 Flash 0731 | Hy4 | Leader |
|---|---|---|---|
| Vals Index | Not measured | 59.4% | Only Hy4 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 |
| 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 | 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
DeepSeek V4 Flash 0731 costs less
Repository review
50K input + 3K output tokens
DeepSeek V4 Flash 0731 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V4 Flash 0731 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 |
|---|---|---|
| Maker | DeepSeek | Tencent |
| Weights | Open weights | Open weights |
| Released | July 31, 2026 | November 4, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $0.14 | $0.417 |
| Output $/Mtok | $0.30 | $1.2505 |
| Coding index | 51.8 | 65.2 |
| 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 for coding?
Pick Hy4 for coding: it scores 65.2 on the Vibe Coding Index against 51.8 for DeepSeek V4 Flash 0731, though on 2 benchmarks against 4. Pick DeepSeek V4 Flash 0731 for output tokens 4.2x cheaper ($0.30 vs $1.2505 per million).
Which is cheaper, DeepSeek V4 Flash 0731 or Hy4?
DeepSeek V4 Flash 0731 costs $0.14 per million input tokens and $0.30 per million output tokens; Hy4 costs $0.417 and $1.2505. Cost per solved task is known for DeepSeek V4 Flash 0731 only.
Which has the bigger context window, DeepSeek V4 Flash 0731 or Hy4?
Neither: both take 1.05M tokens.
How many benchmarks is the DeepSeek V4 Flash 0731 vs Hy4 comparison based on?
4 benchmarks have a result for both models as of November 5, 2026. DeepSeek V4 Flash 0731's coding index rests on 4 independent benchmarks and Hy4's on 2. Where only one model has a result, the page says so instead of naming a winner.