Hy3 preview vs Solar Mini 4
Hy3 preview leads Solar Mini 4 on the Artificial Analysis Intelligence Index, 25.3 to 24.1, and Solar Mini 4 costs 3.0x less per output token ($0.20 vs $0.60 per million). Updated October 21, 2026; 3 benchmarks have a result for both.
Hy3 preview or Solar Mini 4: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Hy3 preview for work measured by Long context reasoning (AA-LCR), where it leads.
- Shared results
- 3
- Hy3 preview only
- 33
- Solar Mini 4 only
- 4
- 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
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Hy3 preview
Hy3 preview leads, 25.3 against 24.1.
Same board, both measured
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 Solar Mini 4 has a Design Arena: websites result, 1159.
Directional only
Long documents
Listed context window
Solar Mini 4
Solar Mini 4 takes 524K tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Solar Mini 4
Hy3 preview $0.0005, Solar Mini 4 $0.0001 per turn.
List prices
At a glance
- Coding index
- Hy3 preview not benchmarked, Solar Mini 4 not benchmarked.
- Widest category
- General, 18.7 points apart on average over 1 shared benchmark.
- Widest single gap
- Long context reasoning (AA-LCR): Hy3 preview 64.7% against Solar Mini 4 83.3%, 18.7 points apart on a 0 to 100 scale.
- Output price
- Hy3 preview $0.60 against Solar Mini 4 $0.20 per million output tokens, 3.0x apart.
- Context window
- Hy3 preview takes 262K 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 | Hy3 preview | Bars | Solar Mini 4 | Ties |
|---|---|---|---|---|
| Intelligence | 1 | 0 | ||
| Reasoning | 1 | 0 | ||
| General | 0 | 1 | ||
| All shared boards | 2 | 1 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index8 boards, none shared
| Benchmark | Hy3 preview | Solar Mini 4 | Leader |
|---|---|---|---|
| LMArena WebDev | 1357 | Not measured | Only Hy3 preview measured |
| AA Coding Index | 58.8 | Not measured | Only Hy3 preview measured |
| SciCode | Not measured | 47.6% | Only Solar Mini 4 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 34.1% | Not measured | Only Hy3 preview measured |
| LMArena Text: coding | 1421 | Not measured | Only Hy3 preview measured |
| LMArena Text: software and IT | 1423 | Not measured | Only Hy3 preview measured |
| LMArena WebDev: React | 1349 | Not measured | Only Hy3 preview measured |
| LMArena WebDev: HTML | 1356 | Not measured | Only Hy3 preview measured |
| Neither model has a result on the other 31 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Hy3 preview | Solar Mini 4 | Leader |
|---|---|---|---|
| AA Intelligence Index | 25.3 | 24.1 | Hy3 preview |
| 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 preview | Solar Mini 4 | Leader |
|---|---|---|---|
| AA Agentic Index | 24.1 | Not measured | Only Hy3 preview measured |
| τ²-Bench Telecom | 92.7% | Not measured | 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 index10
| Benchmark | Hy3 preview | Solar Mini 4 | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 86.7% | Not measured | Only Hy3 preview measured |
| Humanity's Last Exam (Artificial Analysis run) | 27.8% | 25.8% | Hy3 preview |
| LMArena Text: hard prompts | 1413 | Not measured | Only Hy3 preview measured |
| LMArena Text: expert | 1422 | Not measured | Only Hy3 preview measured |
| LMArena Text: hard prompts in English | 1416 | Not measured | Only Hy3 preview measured |
| Neither model has a result on the other 17 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Hy3 preview | Solar Mini 4 | Leader |
|---|---|---|---|
| LMArena Text: math | 1424 | Not measured | Only Hy3 preview measured |
| LMArena Text: mathematical work | 1442 | Not measured | Only Hy3 preview measured |
| Neither model has a result on the other 11 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | Hy3 preview | Solar Mini 4 | Leader |
|---|---|---|---|
| LMArena Text: science | 1416 | Not measured | Only Hy3 preview measured |
| LMArena Text: medicine and healthcare | 1405 | Not measured | Only Hy3 preview measured |
| LMArena Text: legal and government | 1430 | Not measured | Only Hy3 preview measured |
| LMArena Text: business and finance | 1397 | Not measured | Only Hy3 preview measured |
| Neither model has a result on the other 14 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | Hy3 preview | Solar Mini 4 | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1159 | Only Solar Mini 4 measured |
| Design Arena: game dev | Not measured | 1109 | Only Solar Mini 4 measured |
| Design Arena: all code categories | Not measured | 1150 | Only Solar Mini 4 measured |
| Neither model has a result on the other 6 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Hy3 preview | Solar Mini 4 | Leader |
|---|---|---|---|
| IFBench | 63.1% | Not measured | Only Hy3 preview measured |
| Long context reasoning (AA-LCR) | 64.7% | 83.3% | Solar Mini 4 |
| LMArena Text | 1401 | Not measured | Only Hy3 preview measured |
| LMArena Text: instruction following | 1383 | Not measured | Only Hy3 preview measured |
| LMArena Text: creative writing | 1339 | Not measured | Only Hy3 preview measured |
| LMArena Text: English | 1409 | Not measured | Only Hy3 preview measured |
| LMArena Text: non-English | 1390 | Not measured | Only Hy3 preview measured |
| LMArena Text: Chinese | 1435 | Not measured | Only Hy3 preview measured |
| LMArena Text: French | 1425 | Not measured | Only Hy3 preview measured |
| LMArena Text: Spanish | 1399 | Not measured | Only Hy3 preview measured |
| LMArena Text: Russian | 1399 | Not measured | Only Hy3 preview measured |
| LMArena Text: multi-turn | 1411 | Not measured | Only Hy3 preview measured |
| LMArena Text: longer queries | 1402 | Not measured | Only Hy3 preview measured |
| LMArena Text: writing and language | 1370 | Not measured | Only Hy3 preview measured |
| LMArena Text: entertainment and media | 1352 | Not measured | Only Hy3 preview measured |
| Neither model has a result on the other 31 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Hy3 preview | 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 Hy3 preview | Upstage Solar Mini 4 |
|---|---|---|
| Maker | Tencent | Upstage |
| Weights | Open weights | No public weights listed |
| Released | April 22, 2026 | September 23, 2026 |
| Context window | 262K | 524K |
| Input $/Mtok | $0.18 | $0.05 |
| Output $/Mtok | $0.60 | $0.20 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 1 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Hy3 preview better than Solar Mini 4 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Hy3 preview for work measured by Long context reasoning (AA-LCR), where it leads.
Which is cheaper, Hy3 preview or Solar Mini 4?
Hy3 preview costs $0.18 per million input tokens and $0.60 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, Hy3 preview or Solar Mini 4?
Solar Mini 4, with 524K tokens against 262K.
How many benchmarks is the Hy3 preview vs Solar Mini 4 comparison based on?
3 benchmarks have a result for both models as of October 21, 2026. Hy3 preview's coding index rests on 1 independent benchmark and Solar Mini 4's on 0. Where only one model has a result, the page says so instead of naming a winner.