DeepSeek V4 Flash 0423 vs Hy3 preview
Hy3 preview leads DeepSeek V4 Flash 0423 on the Artificial Analysis Intelligence Index, 25.3 to 24.4, and DeepSeek V4 Flash 0423 costs 2.1x less per output token ($0.28 vs $0.60 per million). Updated October 22, 2026; 30 benchmarks have a result for both.
DeepSeek V4 Flash 0423 or Hy3 preview: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick DeepSeek V4 Flash 0423 for output tokens 2.1x cheaper ($0.28 vs $0.60 per million) and a larger context window (1.05M against 262K tokens).
- Shared results
- 30
- DeepSeek V4 Flash 0423 only
- 19
- Hy3 preview only
- 6
- Like-for-like categories
- 7 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
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Hy3 preview
Hy3 preview leads, 25.3 against 24.4.
Same board, both measured
Agentic work
AA Agentic Index
DeepSeek V4 Flash 0423
DeepSeek V4 Flash 0423 leads, 26.3 against 24.1.
Same board, both measured
Web design
Design Arena: websites
No call
Only DeepSeek V4 Flash 0423 has a Design Arena: websites result, 1207.
Directional only
Long documents
Listed context window
DeepSeek V4 Flash 0423
DeepSeek V4 Flash 0423 takes 1.05M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
DeepSeek V4 Flash 0423
DeepSeek V4 Flash 0423 $0.0003, Hy3 preview $0.0005 per turn.
List prices
At a glance
- Coding index
- DeepSeek V4 Flash 0423 not benchmarked, Hy3 preview not benchmarked.
- Widest category
- Coding, 20.5 points apart on average over 6 shared benchmarks.
- Widest single gap
- LMArena WebDev: React: DeepSeek V4 Flash 0423 1585 against Hy3 preview 1349, 39.4 points apart on a 0 to 100 scale.
- Output price
- DeepSeek V4 Flash 0423 $0.28 against Hy3 preview $0.60 per million output tokens, 2.1x apart.
- Context window
- DeepSeek V4 Flash 0423 takes 1.05M tokens, Hy3 preview 262K.
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 0423 | Bars | Hy3 preview | Ties |
|---|---|---|---|---|
| Coding | 5 | 1 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 3 | 0 | ||
| Math | 1 | 1 | ||
| Knowledge | 4 | 0 | ||
| General | 13 | 0 | ||
| All shared boards | 27 | 3 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index51
| Benchmark | DeepSeek V4 Flash 0423 | Hy3 preview | Leader |
|---|---|---|---|
| LMArena WebDev | 1582 | 1357 | DeepSeek V4 Flash 0423 |
| AA Coding Index | 52.0 | 58.8 | Hy3 preview |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 34.1% | Only Hy3 preview measured |
| WeirdML | 45.6% | Not measured | Only DeepSeek V4 Flash 0423 measured |
| ALE-Bench | 678.2 | Not measured | Only DeepSeek V4 Flash 0423 measured |
| LMArena Text: coding | 1457 | 1421 | DeepSeek V4 Flash 0423 |
| LMArena Text: software and IT | 1453 | 1423 | DeepSeek V4 Flash 0423 |
| LMArena WebDev: React | 1585 | 1349 | DeepSeek V4 Flash 0423 |
| LMArena WebDev: HTML | 1558 | 1356 | DeepSeek V4 Flash 0423 |
| Neither model has a result on the other 30 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | DeepSeek V4 Flash 0423 | Hy3 preview | Leader |
|---|---|---|---|
| AA Intelligence Index | 24.4 | 25.3 | Hy3 preview |
| Epoch Capabilities Index | 146.1 | Not measured | Only DeepSeek V4 Flash 0423 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | DeepSeek V4 Flash 0423 | Hy3 preview | Leader |
|---|---|---|---|
| AA Agentic Index | 26.3 | 24.1 | DeepSeek V4 Flash 0423 |
| τ²-Bench Telecom | Not measured | 92.7% | Only Hy3 preview measured |
| Neither model has a result on the other 39 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | DeepSeek V4 Flash 0423 | Hy3 preview | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | Not measured | 86.7% | Only Hy3 preview measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 27.8% | Only Hy3 preview measured |
| SimpleBench | 46.3% | Not measured | Only DeepSeek V4 Flash 0423 measured |
| LMArena Text: hard prompts | 1444 | 1413 | DeepSeek V4 Flash 0423 |
| LMArena Text: expert | 1441 | 1422 | DeepSeek V4 Flash 0423 |
| LMArena Text: hard prompts in English | 1449 | 1416 | DeepSeek V4 Flash 0423 |
| Kagi LLM Benchmark | 52.2% | Not measured | Only DeepSeek V4 Flash 0423 measured |
| Neither model has a result on the other 15 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | DeepSeek V4 Flash 0423 | Hy3 preview | Leader |
|---|---|---|---|
| LMArena Text: math | 1426 | 1424 | DeepSeek V4 Flash 0423 |
| LMArena Text: mathematical work | 1432 | 1442 | Hy3 preview |
| Neither model has a result on the other 11 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | DeepSeek V4 Flash 0423 | Hy3 preview | Leader |
|---|---|---|---|
| LMArena Text: science | 1446 | 1416 | DeepSeek V4 Flash 0423 |
| LMArena Text: medicine and healthcare | 1448 | 1405 | DeepSeek V4 Flash 0423 |
| LMArena Text: legal and government | 1439 | 1430 | DeepSeek V4 Flash 0423 |
| LMArena Text: business and finance | 1425 | 1397 | DeepSeek V4 Flash 0423 |
| 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 0423 | Hy3 preview | Leader |
|---|---|---|---|
| Design Arena: websites | 1207 | Not measured | Only DeepSeek V4 Flash 0423 measured |
| Design Arena: UI components | 1162 | Not measured | Only DeepSeek V4 Flash 0423 measured |
| Design Arena: game dev | 1196 | Not measured | Only DeepSeek V4 Flash 0423 measured |
| Design Arena: data viz | 1127 | Not measured | Only DeepSeek V4 Flash 0423 measured |
| Design Arena: 3D | 1188 | Not measured | Only DeepSeek V4 Flash 0423 measured |
| Design Arena: all code categories | 1205 | Not measured | Only DeepSeek V4 Flash 0423 measured |
| Design Arena: SVG | 1155 | Not measured | Only DeepSeek V4 Flash 0423 measured |
| Design Arena: ASCII art | 1109 | Not measured | Only DeepSeek V4 Flash 0423 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index130
| Benchmark | DeepSeek V4 Flash 0423 | Hy3 preview | Leader |
|---|---|---|---|
| IFBench | Not measured | 63.1% | Only Hy3 preview measured |
| Long context reasoning (AA-LCR) | Not measured | 64.7% | Only Hy3 preview measured |
| DTBench | 86.4% | Not measured | Only DeepSeek V4 Flash 0423 measured |
| LMCA | 35.9% | Not measured | Only DeepSeek V4 Flash 0423 measured |
| LMArena Text | 1432 | 1401 | DeepSeek V4 Flash 0423 |
| LMArena Text: instruction following | 1421 | 1383 | DeepSeek V4 Flash 0423 |
| LMArena Text: creative writing | 1403 | 1339 | DeepSeek V4 Flash 0423 |
| LMArena Text: English | 1441 | 1409 | DeepSeek V4 Flash 0423 |
| LMArena Text: non-English | 1419 | 1390 | DeepSeek V4 Flash 0423 |
| LMArena Text: Chinese | 1463 | 1435 | DeepSeek V4 Flash 0423 |
| LMArena Text: German | 1419 | Not measured | Only DeepSeek V4 Flash 0423 measured |
| LMArena Text: Japanese | 1389 | Not measured | Only DeepSeek V4 Flash 0423 measured |
| LMArena Text: Korean | 1383 | Not measured | Only DeepSeek V4 Flash 0423 measured |
| LMArena Text: French | 1439 | 1425 | DeepSeek V4 Flash 0423 |
| LMArena Text: Spanish | 1436 | 1399 | DeepSeek V4 Flash 0423 |
| LMArena Text: Russian | 1427 | 1399 | DeepSeek V4 Flash 0423 |
| LMArena Text: Polish | 1436 | Not measured | Only DeepSeek V4 Flash 0423 measured |
| LMArena Text: multi-turn | 1449 | 1411 | DeepSeek V4 Flash 0423 |
| LMArena Text: longer queries | 1434 | 1402 | DeepSeek V4 Flash 0423 |
| LMArena Text: writing and language | 1410 | 1370 | DeepSeek V4 Flash 0423 |
| LMArena Text: entertainment and media | 1400 | 1352 | DeepSeek V4 Flash 0423 |
| Neither model has a result on the other 25 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | DeepSeek V4 Flash 0423 | Hy3 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 V4 Flash 0423 costs less
Repository review
50K input + 3K output tokens
DeepSeek V4 Flash 0423 costs less
Agent loop
200K input + 10K output tokens
DeepSeek V4 Flash 0423 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 0423 | Tencent Hy3 preview |
|---|---|---|
| Maker | DeepSeek | Tencent |
| Weights | Open weights | Open weights |
| Released | April 24, 2026 | April 22, 2026 |
| Context window | 1.05M | 262K |
| Input $/Mtok | $0.14 | $0.18 |
| Output $/Mtok | $0.28 | $0.60 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is DeepSeek V4 Flash 0423 better than Hy3 preview for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick DeepSeek V4 Flash 0423 for output tokens 2.1x cheaper ($0.28 vs $0.60 per million) and a larger context window (1.05M against 262K tokens).
Which is cheaper, DeepSeek V4 Flash 0423 or Hy3 preview?
DeepSeek V4 Flash 0423 costs $0.14 per million input tokens and $0.28 per million output tokens; Hy3 preview costs $0.18 and $0.60. Cost per solved task is known for neither of them.
Which has the bigger context window, DeepSeek V4 Flash 0423 or Hy3 preview?
DeepSeek V4 Flash 0423, with 1.05M tokens against 262K.
How many benchmarks is the DeepSeek V4 Flash 0423 vs Hy3 preview comparison based on?
30 benchmarks have a result for both models as of October 22, 2026. DeepSeek V4 Flash 0423's coding index rests on 1 independent benchmark and Hy3 preview's on 1. Where only one model has a result, the page says so instead of naming a winner.