Hy3 vs Hy3 preview
Hy3 and Hy3 preview cost about the same per output token ($0.528 vs $0.60 per million). Updated October 22, 2026; 30 benchmarks have a result for both.
Hy3 or Hy3 preview: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Hy3 for output tokens 1.1x cheaper ($0.528 vs $0.60 per million) and work measured by LMArena Text: legal and government, where it leads.
- Shared results
- 30
- Hy3 only
- 14
- Hy3 preview only
- 6
- Like-for-like categories
- 5 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
No call
Only Hy3 preview has a AA Intelligence Index result, 25.3.
Directional only
Agentic work
AA Agentic Index
No call
Only Hy3 preview has a AA Agentic Index result, 24.1.
Directional only
Web design
Design Arena: websites
No call
Only Hy3 has a Design Arena: websites result, 1230.
Directional only
Long documents
Listed context window
No call
Both take 262K tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Hy3
Hy3 $0.0004, Hy3 preview $0.0005 per turn.
List prices
At a glance
- Coding index
- Hy3 not benchmarked, Hy3 preview not benchmarked.
- Widest category
- Coding, 16.8 points apart on average over 5 shared benchmarks.
- Widest single gap
- LMArena WebDev: React: Hy3 1511 against Hy3 preview 1349, 27.0 points apart on a 0 to 100 scale.
- Output price
- Hy3 $0.528 against Hy3 preview $0.60 per million output tokens, 1.1x apart.
- Context window
- Both take 262K 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 | Hy3 | Bars | Hy3 preview | Ties |
|---|---|---|---|---|
| Coding | 5 | 0 | ||
| Reasoning | 5 | 0 | ||
| Math | 2 | 0 | ||
| Knowledge | 3 | 1 | ||
| General | 14 | 0 | ||
| All shared boards | 29 | 1 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index50
| Benchmark | Hy3 | Hy3 preview | Leader |
|---|---|---|---|
| LMArena WebDev | 1507 | 1357 | Hy3 |
| AA Coding Index | Not measured | 58.8 | Only Hy3 preview measured |
| SciCode | 48.6% | Not measured | Only Hy3 measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 34.1% | Only Hy3 preview measured |
| ALE-Bench | 838.6 | Not measured | Only Hy3 measured |
| LMArena Text: coding | 1466 | 1421 | Hy3 |
| LMArena Text: software and IT | 1463 | 1423 | Hy3 |
| LMArena WebDev: React | 1511 | 1349 | Hy3 |
| LMArena WebDev: HTML | 1487 | 1356 | Hy3 |
| Neither model has a result on the other 30 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Hy3 | Hy3 preview | Leader |
|---|---|---|---|
| AA Intelligence Index | Not measured | 25.3 | Only Hy3 preview measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Hy3 | Hy3 preview | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 24.1 | Only Hy3 preview measured |
| 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 index50
| Benchmark | Hy3 | Hy3 preview | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 89.7% | 86.7% | Hy3 |
| Humanity's Last Exam (Artificial Analysis run) | 33.5% | 27.8% | Hy3 |
| LMArena Text: hard prompts | 1447 | 1413 | Hy3 |
| LMArena Text: expert | 1461 | 1422 | Hy3 |
| LMArena Text: hard prompts in English | 1455 | 1416 | Hy3 |
| Neither model has a result on the other 17 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Hy3 | Hy3 preview | Leader |
|---|---|---|---|
| LMArena Text: math | 1473 | 1424 | Hy3 |
| LMArena Text: mathematical work | 1482 | 1442 | Hy3 |
| Neither model has a result on the other 11 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index31
| Benchmark | Hy3 | Hy3 preview | Leader |
|---|---|---|---|
| LMArena Text: science | 1457 | 1416 | Hy3 |
| LMArena Text: medicine and healthcare | 1452 | 1405 | Hy3 |
| LMArena Text: legal and government | 1422 | 1430 | Hy3 preview |
| LMArena Text: business and finance | 1424 | 1397 | Hy3 |
| 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 | Hy3 | Hy3 preview | Leader |
|---|---|---|---|
| Design Arena: websites | 1230 | Not measured | Only Hy3 measured |
| Design Arena: UI components | 1204 | Not measured | Only Hy3 measured |
| Design Arena: game dev | 1208 | Not measured | Only Hy3 measured |
| Design Arena: data viz | 1164 | Not measured | Only Hy3 measured |
| Design Arena: 3D | 1232 | Not measured | Only Hy3 measured |
| Design Arena: all code categories | 1227 | Not measured | Only Hy3 measured |
| Design Arena: SVG | 1200 | Not measured | Only Hy3 measured |
| Design Arena: ASCII art | 1152 | Not measured | Only Hy3 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index140
| Benchmark | Hy3 | Hy3 preview | Leader |
|---|---|---|---|
| IFBench | Not measured | 63.1% | Only Hy3 preview measured |
| Long context reasoning (AA-LCR) | 79.0% | 64.7% | Hy3 |
| LMArena Text | 1438 | 1401 | Hy3 |
| LMArena Text: instruction following | 1426 | 1383 | Hy3 |
| LMArena Text: creative writing | 1403 | 1339 | Hy3 |
| LMArena Text: English | 1448 | 1409 | Hy3 |
| LMArena Text: non-English | 1426 | 1390 | Hy3 |
| LMArena Text: Chinese | 1485 | 1435 | Hy3 |
| LMArena Text: German | 1449 | Not measured | Only Hy3 measured |
| LMArena Text: Japanese | 1397 | Not measured | Only Hy3 measured |
| LMArena Text: Korean | 1396 | Not measured | Only Hy3 measured |
| LMArena Text: French | 1456 | 1425 | Hy3 |
| LMArena Text: Spanish | 1457 | 1399 | Hy3 |
| LMArena Text: Russian | 1432 | 1399 | Hy3 |
| LMArena Text: Polish | 1447 | Not measured | Only Hy3 measured |
| LMArena Text: multi-turn | 1436 | 1411 | Hy3 |
| LMArena Text: longer queries | 1442 | 1402 | Hy3 |
| LMArena Text: writing and language | 1414 | 1370 | Hy3 |
| LMArena Text: entertainment and media | 1400 | 1352 | Hy3 |
| Neither model has a result on the other 27 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Hy3 | 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
Hy3 costs less
Repository review
50K input + 3K output tokens
Hy3 costs less
Agent loop
200K input + 10K output tokens
Hy3 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 | Tencent Hy3 | Tencent Hy3 preview |
|---|---|---|
| Maker | Tencent | Tencent |
| Weights | Open weights | Open weights |
| Released | July 6, 2026 | April 22, 2026 |
| Context window | 262K | 262K |
| Input $/Mtok | $0.132 | $0.18 |
| Output $/Mtok | $0.528 | $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 Hy3 better than Hy3 preview for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Hy3 for output tokens 1.1x cheaper ($0.528 vs $0.60 per million) and work measured by LMArena Text: legal and government, where it leads.
Which is cheaper, Hy3 or Hy3 preview?
Hy3 costs $0.132 per million input tokens and $0.528 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, Hy3 or Hy3 preview?
Neither: both take 262K tokens.
How many benchmarks is the Hy3 vs Hy3 preview comparison based on?
30 benchmarks have a result for both models as of October 22, 2026. Hy3'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.