Model comparison
Hy3 vs Solar Pro4
Hy3 is the stronger model overall, scoring 44.2 to 42.1 on the Noometry Index.
Last verified . 18 shared benchmarks.
Tencent
UpstageSummary
- They share 18 benchmarks with published results for both. Hy3 scores higher in 7 categories and Solar Pro4 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Hy3 leads 46.8 to 40.1.
- Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $0.30 / $1.20 for Solar Pro4.
- Solar Pro4 accepts more context: 524K tokens versus 262K.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| Hy3 | Solar Pro4 | |
|---|---|---|
| Provider | Tencent | Upstage |
| Noometry Index | 44.2 | 42.1 |
| Released | 2026-07-06 | 2026-08-06 |
| Weights | Open | Proprietary |
| Context window | 262K | 524K |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.0825 | $0.30 |
| Output $ / M tokens | $0.33 | $1.20 |
| Results tracked | 19 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), Solar Pro4: 40.1 (#149)
| Benchmark | Hy3 | Solar Pro4 |
|---|---|---|
| LMArena WebDev | 1508 | 1371 |
| LMArena Coding | 1464 | 1437 |
Reasoning Solar Pro4 leads
Hy3: 26.1 (#136), Solar Pro4: 28.5 (#104)
| Benchmark | Hy3 | Solar Pro4 |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1399 |
| NYT Connections (extended) | 41.2% | — |
Math Hy3 leads
Hy3: 40.1 (#93), Solar Pro4: 38.8 (#128)
| Benchmark | Hy3 | Solar Pro4 |
|---|---|---|
| LMArena Math | 1475 | 1416 |
Knowledge Hy3 leads
Hy3: 40.8 (#114), Solar Pro4: 39.8 (#129)
| Benchmark | Hy3 | Solar Pro4 |
|---|---|---|
| LMArena Expert | 1460 | 1427 |
Multilingual Hy3 leads
Hy3: 53.5 (#65), Solar Pro4: 48.7 (#139)
| Benchmark | Hy3 | Solar Pro4 |
|---|---|---|
| LMArena Non-English | 1426 | 1361 |
| LMArena Chinese | 1493 | 1415 |
| LMArena French | 1461 | 1397 |
| LMArena German | 1439 | 1364 |
| LMArena Japanese | 1392 | 1309 |
| LMArena Korean | 1395 | 1382 |
| LMArena Russian | 1432 | 1360 |
| LMArena Spanish | 1456 | 1401 |
Instruction Following Hy3 leads
Hy3: 75.1 (#70), Solar Pro4: 72.7 (#132)
| Benchmark | Hy3 | Solar Pro4 |
|---|---|---|
| LMArena Instruction Following | 1426 | 1377 |
Long Context Hy3 leads
Hy3: 44.1 (#75), Solar Pro4: 42.1 (#130)
| Benchmark | Hy3 | Solar Pro4 |
|---|---|---|
| LMArena Longer Query | 1442 | 1381 |
Writing & Preference Hy3 leads
Hy3: 62.2 (#81), Solar Pro4: 56.5 (#138)
| Benchmark | Hy3 | Solar Pro4 |
|---|---|---|
| LMArena Text | 1439 | 1386 |
| LMArena Creative Writing | 1402 | 1316 |
| LMArena Multi-Turn | 1436 | 1385 |
Frequently asked questions
Is Hy3 better than Solar Pro4?
Hy3 is the stronger model overall, scoring 44.2 to 42.1 on the Noometry Index.
Which is cheaper, Hy3 or Solar Pro4?
Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; Solar Pro4 lists at $0.30 and $1.20.
Is Hy3 or Solar Pro4 better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 40.1 in the Noometry coding category.
Which has the bigger context window?
Solar Pro4 does, with 524K tokens against 262K.
How many benchmarks do Hy3 and Solar Pro4 share?
18 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Solar Pro4 has 18.