Model comparison
Hy3 vs Step 1o Turbo 202506
Hy3 is the stronger model overall, scoring 44.2 to 39.7 on the Noometry Index.
Last verified . 13 shared benchmarks.
Tencent
StepFunSummary
- They share 13 benchmarks with published results for both. Hy3 scores higher in 7 categories and Step 1o Turbo 202506 in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hy3 leads 62.2 to 53.1.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| Hy3 | Step 1o Turbo 202506 | |
|---|---|---|
| Provider | Tencent | StepFun |
| Noometry Index | 44.2 | 39.7 |
| Released | 2026-07-06 | — |
| Weights | Open | Proprietary |
| Context window | 262K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.13 | — |
| Output $ / M tokens | $0.53 | — |
| Results tracked | 19 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.8 (#63), Step 1o Turbo 202506: 39.2 (#160)
| Benchmark | Hy3 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Coding | 1464 | 1339 |
| LMArena WebDev | 1508 | — |
Reasoning Too close to call
Hy3: 26.1 (#136), Step 1o Turbo 202506: 26.8 (#129)
| Benchmark | Hy3 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1335 |
| NYT Connections (extended) | 41.2% | — |
Math Hy3 leads
Hy3: 40.1 (#93), Step 1o Turbo 202506: 36.6 (#164)
| Benchmark | Hy3 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Math | 1475 | 1318 |
Knowledge Hy3 leads
Hy3: 40.8 (#114), Step 1o Turbo 202506: 36.1 (#176)
| Benchmark | Hy3 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Expert | 1460 | 1308 |
Multimodal Not comparable
Hy3: —, Step 1o Turbo 202506: 36.1 (#80)
| Benchmark | Hy3 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Vision | — | 1186 |
Multilingual Hy3 leads
Hy3: 53.5 (#65), Step 1o Turbo 202506: 45.3 (#173)
| Benchmark | Hy3 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Non-English | 1426 | 1313 |
| LMArena Chinese | 1493 | 1380 |
| LMArena German | 1439 | 1314 |
| LMArena Russian | 1432 | 1327 |
| LMArena French | 1461 | — |
| LMArena Japanese | 1392 | — |
| LMArena Korean | 1395 | — |
| LMArena Spanish | 1456 | — |
Instruction Following Hy3 leads
Hy3: 75.1 (#70), Step 1o Turbo 202506: 69.2 (#176)
| Benchmark | Hy3 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Instruction Following | 1426 | 1310 |
Long Context Hy3 leads
Hy3: 44.1 (#75), Step 1o Turbo 202506: 41.0 (#146)
| Benchmark | Hy3 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Longer Query | 1442 | 1348 |
Writing & Preference Hy3 leads
Hy3: 62.2 (#81), Step 1o Turbo 202506: 53.1 (#160)
| Benchmark | Hy3 | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Text | 1439 | 1336 |
| LMArena Creative Writing | 1402 | 1307 |
| LMArena Multi-Turn | 1436 | 1340 |
Frequently asked questions
Is Hy3 better than Step 1o Turbo 202506?
Hy3 is the stronger model overall, scoring 44.2 to 39.7 on the Noometry Index.
Is Hy3 or Step 1o Turbo 202506 better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 39.2 in the Noometry coding category.
How many benchmarks do Hy3 and Step 1o Turbo 202506 share?
13 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Step 1o Turbo 202506 has 14.