Hy4 vs Hy4 preview
Hy4 leads Hy4 preview on coding, 65.2 to 44.3 on the Vibe Coding Index, and Hy4 costs 2.0x less per output token ($1.2505 vs $2.501 per million). Updated November 5, 2026; 6 benchmarks have a result for both.
Hy4 or Hy4 preview: which to pick
Pick Hy4 for coding: it scores 65.2 on the Vibe Coding Index against 44.3 for Hy4 preview, though on 2 benchmarks against 3.
Pick Hy4 preview for work measured by Legal Research Bench (Vals AI), where it leads.
- Shared results
- 6
- Hy4 only
- 0
- Hy4 preview only
- 19
- 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
Hy4
Hy4 scores 65.2 against 44.3.
2 and 3 benchmarks behind the scores
General
Vals Index
Hy4
Hy4 leads, 59.4% against 53.2%.
Same board, both measured
Long documents
Listed context window
No call
Both take 1.05M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Hy4
Hy4 $0.0010, Hy4 preview $0.0021 per turn.
List prices
At a glance
- Coding index
- Hy4 65.2 from 2 benchmarks, Hy4 preview 44.3 from 3 benchmarks.
- Widest category
- Coding, 22.6 points apart on average over 2 shared benchmarks.
- Widest single gap
- Terminal-Bench 4 (Vals AI): Hy4 39.4% against Hy4 preview 8.1%, 41.7 points apart on a 0 to 100 scale.
- Output price
- Hy4 $1.2505 against Hy4 preview $2.501 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 | Hy4 | Bars | Hy4 preview | Ties |
|---|---|---|---|---|
| Coding | 2 | 0 | ||
| Agentic work | 2 | 1 | ||
| General | 1 | 0 | ||
| All shared boards | 5 | 1 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index20
| Benchmark | Hy4 | Hy4 preview | Leader |
|---|---|---|---|
| LMArena WebDev | Not measured | 1631 | Only Hy4 preview measured |
| Terminal-Bench 4 (Vals AI) | 39.4% | 8.1% | Hy4 |
| Vibe Code Bench (Vals AI) | 81.0% | 77.5% | Hy4 |
| 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 |
| GameBench 2 | Not measured | 61.4 | Only Hy4 preview measured |
| Neither model has a result on the other 39 boards here | |||
IntelligenceNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Hy4 | Hy4 preview | Leader |
|---|---|---|---|
| Neither model has a result on 2 boards here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index21
| Benchmark | Hy4 | 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) | 34.4% | 32.6% | Hy4 |
| Legal Research Bench (Vals AI) | 41.4% | 45.2% | Hy4 preview |
| Harvey's Legal Agent Benchmark (Vals AI) | 12.5% | 8.8% | Hy4 |
| 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 36 boards here | |||
ReasoningNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Hy4 | Hy4 preview | Leader |
|---|---|---|---|
| Neither model has a result on 24 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Hy4 | Hy4 preview | Leader |
|---|---|---|---|
| ProofBench | Not measured | 75.0% | Only Hy4 preview measured |
| Neither model has a result on the other 13 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Hy4 | 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 18 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Hy4 | Hy4 preview | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Hy4 | Hy4 preview | Leader |
|---|---|---|---|
| Vals Index | 59.4% | 53.2% | Hy4 |
| Public Benefits Bench (Vals AI) | Not measured | 68.6% | Only Hy4 preview measured |
| MedScribe (Vals AI) | Not measured | 83.6% | Only Hy4 preview measured |
| Neither model has a result on the other 45 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Hy4 | 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
Hy4 costs less
Repository review
50K input + 3K output tokens
Hy4 costs less
Agent loop
200K input + 10K output tokens
Hy4 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 Hy4 | Tencent Hy4 preview |
|---|---|---|
| Maker | Tencent | Tencent |
| Weights | Open weights | Open weights |
| Released | November 4, 2026 | August 28, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $0.417 | $0.834 |
| Output $/Mtok | $1.2505 | $2.501 |
| Coding index | 65.2 | 44.3 |
| Independent measurements behind it | 2 | 3 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Hy4 better than Hy4 preview for coding?
Pick Hy4 for coding: it scores 65.2 on the Vibe Coding Index against 44.3 for Hy4 preview, though on 2 benchmarks against 3. Pick Hy4 preview for work measured by Legal Research Bench (Vals AI), where it leads.
Which is cheaper, Hy4 or Hy4 preview?
Hy4 costs $0.417 per million input tokens and $1.2505 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, Hy4 or Hy4 preview?
Neither: both take 1.05M tokens.
How many benchmarks is the Hy4 vs Hy4 preview comparison based on?
6 benchmarks have a result for both models as of November 5, 2026. Hy4's coding index rests on 2 independent benchmarks and Hy4 preview's on 3. Where only one model has a result, the page says so instead of naming a winner.