DeepSeek V3 vs Hy4 preview
Updated October 21, 2026. 0 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
DeepSeek V3 scores 70.2 and Hy4 preview 61.6 on the Vibe Coding Index, but no coding benchmark measured both, so the gap is directional, not a ranking.
Pick DeepSeek V3 when output tokens cost 2.4x less; pick Hy4 preview when the context window is larger, 1.05M against 164K tokens.
- Shared results
- 0
- DeepSeek V3 only
- 13
- Hy4 preview only
- 24
- Like-for-like categories
- 0 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.
Coding
Vibe Coding Index, four public coding benchmarks
No call
70.2 against 61.6, from different benchmarks with none in common.
Directional only
Web design
Design Arena: websites
No call
Only DeepSeek V3 has a Design Arena: websites result, 1120.
Directional only
General
Vals Index
No call
Only Hy4 preview has a Vals Index result, 53.2%.
Directional only
Long documents
Listed context window
Hy4 preview
Hy4 preview takes 1.05M tokens against 164K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V3
DeepSeek V3 $0.0008, Hy4 preview $0.0021 per turn.
List prices
At a glance
- Coding index
- DeepSeek V3 70.2 from 1 benchmark, Hy4 preview 61.6 from 1 benchmark.
- Widest category
- No category has a result for both models.
- Widest single gap
- No benchmark has a result for both models.
- Output price
- DeepSeek V3 $1.0287 against Hy4 preview $2.501 per million output tokens, 2.4x apart.
- Context window
- DeepSeek V3 takes 164K tokens, Hy4 preview 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.
CodingDirectional onlyFour of these boards feed the Vibe Coding Index12 boards, none shared
| Benchmark | DeepSeek V3 | Hy4 preview | Leader |
|---|---|---|---|
| Aider polyglot | 70.2% | Not measured | Only DeepSeek V3 measured |
| SWE-bench Lite | 30.7% | Not measured | Only DeepSeek V3 measured |
| LMArena WebDev | Not measured | 1631 | Only Hy4 preview measured |
| Terminal-Bench 4 (Vals AI) | Not measured | 8.1% | Only Hy4 preview measured |
| Vibe Code Bench (Vals AI) | Not measured | 77.5% | Only Hy4 preview measured |
| Code migration (Vals AI) | Not measured | 47.4% | Only Hy4 preview measured |
| ProgramBench (Vals AI) | Not measured | 0.0% | Only Hy4 preview measured |
| IOI (Vals AI) | Not measured | 59.3% | Only Hy4 preview measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 55.1% | Only Hy4 preview measured |
| CyberBench (Vals AI) | Not measured | 65.4% | Only Hy4 preview measured |
| LMArena WebDev: React | Not measured | 1653 | Only Hy4 preview measured |
| LMArena WebDev: HTML | Not measured | 1620 | Only Hy4 preview measured |
| Neither model has a result on the other 26 boards here | |||
IntelligenceNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V3 | Hy4 preview | Leader |
|---|---|---|---|
| Neither model has a result on 2 boards here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | DeepSeek V3 | Hy4 preview | Leader |
|---|---|---|---|
| SREBench (Vals AI) | Not measured | 2.3% | Only Hy4 preview measured |
| Finance Agent (Vals AI) | Not measured | 55.1% | Only Hy4 preview measured |
| Tax Agent Bench (Vals AI) | Not measured | 32.6% | Only Hy4 preview measured |
| Legal Research Bench (Vals AI) | Not measured | 45.2% | Only Hy4 preview measured |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 8.8% | Only Hy4 preview measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 58.1% | Only Hy4 preview measured |
| BioMysteryBench (Vals AI) | Not measured | 69.3% | Only Hy4 preview measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 1.4% | Only Hy4 preview measured |
| Neither model has a result on the other 31 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | DeepSeek V3 | Hy4 preview | Leader |
|---|---|---|---|
| GPQA Diamond (Epoch AI run) | 71.2% | Not measured | Only DeepSeek V3 measured |
| Neither model has a result on the other 20 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | DeepSeek V3 | Hy4 preview | Leader |
|---|---|---|---|
| OTIS Mock AIME | 48.9% | Not measured | Only DeepSeek V3 measured |
| ProofBench | Not measured | 75.0% | Only Hy4 preview measured |
| Neither model has a result on the other 11 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | DeepSeek V3 | Hy4 preview | Leader |
|---|---|---|---|
| LegalBench (Vals AI) | Not measured | 83.8% | Only Hy4 preview measured |
| MedCode (Vals AI) | Not measured | 43.3% | Only Hy4 preview measured |
| Neither model has a result on the other 15 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | DeepSeek V3 | Hy4 preview | Leader |
|---|---|---|---|
| Design Arena: websites | 1120 | Not measured | Only DeepSeek V3 measured |
| Design Arena: UI components | 1093 | Not measured | Only DeepSeek V3 measured |
| Design Arena: game dev | 1054 | Not measured | Only DeepSeek V3 measured |
| Design Arena: data viz | 1089 | Not measured | Only DeepSeek V3 measured |
| Design Arena: 3D | 1087 | Not measured | Only DeepSeek V3 measured |
| Design Arena: all code categories | 1108 | Not measured | Only DeepSeek V3 measured |
| Design Arena: SVG | 976 | Not measured | Only DeepSeek V3 measured |
| Neither model has a result on the other 2 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | DeepSeek V3 | Hy4 preview | Leader |
|---|---|---|---|
| Vals Index | Not measured | 53.2% | Only Hy4 preview measured |
| Public Benefits Bench (Vals AI) | Not measured | 68.6% | Only Hy4 preview measured |
| MedScribe (Vals AI) | Not measured | 83.6% | Only Hy4 preview measured |
| DTBench | 62.7% | Not measured | Only DeepSeek V3 measured |
| LMCA | 15.2% | Not measured | Only DeepSeek V3 measured |
| Neither model has a result on the other 41 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V3 | Hy4 preview | 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 V3 costs less
Repository review
50K input + 3K output tokens
DeepSeek V3 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V3 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 V3 | Tencent Hy4 preview |
|---|---|---|
| Maker | DeepSeek | Tencent |
| Weights | Open weights | Open weights |
| Released | December 26, 2024 | August 28, 2026 |
| Context window | 164K | 1.05M |
| Input $/Mtok | $0.2574 | $0.834 |
| Output $/Mtok | $1.0287 | $2.501 |
| Coding index | 70.2 | 61.6 |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V3 better than Hy4 preview for coding?
DeepSeek V3 scores 70.2 and Hy4 preview 61.6 on the Vibe Coding Index, but no coding benchmark measured both, so the gap is directional, not a ranking. Pick DeepSeek V3 when output tokens cost 2.4x less; pick Hy4 preview when the context window is larger, 1.05M against 164K tokens.
Which is cheaper, DeepSeek V3 or Hy4 preview?
DeepSeek V3 costs $0.2574 per million input tokens and $1.0287 per million output tokens; Hy4 preview costs $0.834 and $2.501. Cost per solved task is known for neither of them.
Which has the bigger context window, DeepSeek V3 or Hy4 preview?
Hy4 preview, with 1.05M tokens against 164K.
How many benchmarks is the DeepSeek V3 vs Hy4 preview comparison based on?
0 benchmarks have a result for both models as of October 21, 2026. DeepSeek V3's coding index rests on 1 independent benchmark and Hy4 preview's on 1. Where only one model has a result, the page says so instead of naming a winner.