Hy4 vs Solar Mini 4
Solar Mini 4 costs 6.3x less per output token than Hy4 ($0.20 vs $1.2505 per million). Updated November 14, 2026; 7 benchmarks have a result for both.
Hy4 or Solar Mini 4: which to pick
Only Hy4 has a coding score, 65.2 on the Vibe Coding Index; Solar Mini 4 has none, so the two cannot be ranked on coding.
Pick Solar Mini 4 for output tokens 6.3x cheaper ($0.20 vs $1.2505 per million).
- Shared results
- 7
- Hy4 only
- 12
- Solar Mini 4 only
- 5
- 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
No call
Only Hy4 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
No call
Only Hy4 has a AA Intelligence Index result, 34.6.
Directional only
Web design
Design Arena: websites
Hy4
Hy4 leads, 1251 against 1144.
Same board, both measured
General
Vals Index
No call
Only Hy4 has a Vals Index result, 59.4%.
Directional only
Long documents
Listed context window
Hy4
Hy4 takes 1.05M tokens against 524K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Solar Mini 4
Hy4 $0.0010, Solar Mini 4 $0.0001 per turn.
List prices
At a glance
- Coding index
- Hy4 65.2 from 2 benchmarks, Solar Mini 4 not benchmarked.
- Widest category
- Coding, 36.4 points apart on average over 1 shared benchmark.
- Widest single gap
- Terminal-Bench 4.0 (Artificial Analysis run): Hy4 37.4% against Solar Mini 4 1.0%, 36.4 points apart on a 0 to 100 scale.
- Output price
- Hy4 $1.2505 against Solar Mini 4 $0.20 per million output tokens, 6.3x apart.
- Context window
- Hy4 takes 1.05M tokens, Solar Mini 4 524K.
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 | Solar Mini 4 | Ties |
|---|---|---|---|---|
| Coding | 1 | 0 | ||
| Knowledge | 1 | 0 | ||
| Web design | 5 | 0 | ||
| All shared boards | 7 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index10
| Benchmark | Hy4 | Solar Mini 4 | Leader |
|---|---|---|---|
| Terminal-Bench 4 (Vals AI) | 39.4% | Not measured | Only Hy4 measured |
| Vibe Code Bench (Vals AI) | 81.0% | Not measured | Only Hy4 measured |
| SciCode | Not measured | 47.6% | Only Solar Mini 4 measured |
| Terminal-Bench 4.0 (Artificial Analysis run) | 37.4% | 1.0% | Hy4 |
| FrontierCode 2.0 | 31.4% | Not measured | Only Hy4 measured |
| GameBench 2 | 48.7 | Not measured | Only Hy4 measured |
| Terminal-Bench 4.0 | 39.1% | Not measured | Only Hy4 measured |
| Neither model has a result on the other 45 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | Hy4 | Solar Mini 4 | Leader |
|---|---|---|---|
| AA Intelligence Index | 34.6 | Not measured | Only Hy4 measured |
| Neither model has a result on the other 1 board here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | Hy4 | Solar Mini 4 | Leader |
|---|---|---|---|
| Tax Agent Bench (Vals AI) | 34.4% | Not measured | Only Hy4 measured |
| Legal Research Bench (Vals AI) | 41.4% | Not measured | Only Hy4 measured |
| Harvey's Legal Agent Benchmark (Vals AI) | 12.5% | Not measured | Only Hy4 measured |
| Neither model has a result on the other 41 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | Hy4 | Solar Mini 4 | Leader |
|---|---|---|---|
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 25.8% | Only Solar Mini 4 measured |
| HLE-Diamond (Artificial Analysis run) | 32.7% | Not measured | Only Hy4 measured |
| CritPt v2, hard subset (Artificial Analysis run) | 39.0% | Not measured | Only Hy4 measured |
| Neither model has a result on the other 23 boards here | |||
MathNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Hy4 | Solar Mini 4 | Leader |
|---|---|---|---|
| Neither model has a result on 14 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Hy4 | Solar Mini 4 | Leader |
|---|---|---|---|
| AA-Omniscience | 5.4 | -11.6 | Hy4 |
| Neither model has a result on the other 20 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Hy4 | Solar Mini 4 | Leader |
|---|---|---|---|
| Design Arena: websites | 1251 | 1144 | Hy4 |
| Design Arena: UI components | 1197 | 1087 | Hy4 |
| Design Arena: game dev | 1271 | 1097 | Hy4 |
| Design Arena: data viz | Not measured | 1135 | Only Solar Mini 4 measured |
| Design Arena: 3D | 1251 | 1084 | Hy4 |
| Design Arena: all code categories | 1254 | 1127 | Hy4 |
| Neither model has a result on the other 3 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | Hy4 | Solar Mini 4 | Leader |
|---|---|---|---|
| Vals Index | 59.4% | Not measured | Only Hy4 measured |
| Long context reasoning (AA-LCR) | Not measured | 83.3% | Only Solar Mini 4 measured |
| GDPval-AA | Not measured | 1092 | Only Solar Mini 4 measured |
| Neither model has a result on the other 46 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Hy4 | Solar Mini 4 | 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
Solar Mini 4 costs less
Repository review
50K input + 3K output tokens
Solar Mini 4 costs less
Agent loop
200K input + 10K output tokens
Solar Mini 4 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 | Upstage Solar Mini 4 |
|---|---|---|
| Maker | Tencent | Upstage |
| Weights | Open weights | No public weights listed |
| Released | November 4, 2026 | September 23, 2026 |
| Context window | 1.05M | 524K |
| Input $/Mtok | $0.417 | $0.05 |
| Output $/Mtok | $1.2505 | $0.20 |
| Coding index | 65.2 | Not benchmarked |
| Independent measurements behind it | 2 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Hy4 better than Solar Mini 4 for coding?
Only Hy4 has a coding score, 65.2 on the Vibe Coding Index; Solar Mini 4 has none, so the two cannot be ranked on coding. Pick Solar Mini 4 for output tokens 6.3x cheaper ($0.20 vs $1.2505 per million).
Which is cheaper, Hy4 or Solar Mini 4?
Hy4 costs $0.417 per million input tokens and $1.2505 per million output tokens; Solar Mini 4 costs $0.05 and $0.20. Cost per solved task is known for neither of them.
Which has the bigger context window, Hy4 or Solar Mini 4?
Hy4, with 1.05M tokens against 524K.
How many benchmarks is the Hy4 vs Solar Mini 4 comparison based on?
7 benchmarks have a result for both models as of November 14, 2026. Hy4's coding index rests on 2 independent benchmarks and Solar Mini 4's on 0. Where only one model has a result, the page says so instead of naming a winner.