Model comparison
Hy3 vs Step 2 16k Exp 202412
Hy3 is the stronger model overall, scoring 43.6 to 38.6 on the Noometry Index.
Last verified . 12 shared benchmarks.
Tencent
StepFunSummary
- They share 12 benchmarks with published results for both. Hy3 scores higher in 8 categories and Step 2 16k Exp 202412 in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hy3 leads 62.5 to 52.5.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| Hy3 | Step 2 16k Exp 202412 | |
|---|---|---|
| Provider | Tencent | StepFun |
| Noometry Index | 43.6 | 38.6 |
| 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 | 17 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Hy3: 46.6 (#60), Step 2 16k Exp 202412: 37.9 (#170)
| Benchmark | Hy3 | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Coding | 1465 | 1316 |
| LMArena WebDev | 1509 | — |
Reasoning Too close to call
Hy3: 25.0 (#134), Step 2 16k Exp 202412: 24.8 (#140)
| Benchmark | Hy3 | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Hard Prompts | 1449 | 1299 |
| NYT Connections (extended) | 41.2% | — |
Math Hy3 leads
Hy3: 37.4 (#98), Step 2 16k Exp 202412: 33.6 (#171)
| Benchmark | Hy3 | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Math | 1475 | 1305 |
Knowledge Hy3 leads
Hy3: 40.2 (#108), Step 2 16k Exp 202412: 34.6 (#187)
| Benchmark | Hy3 | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Expert | 1461 | 1279 |
Multilingual Hy3 leads
Hy3: 53.7 (#60), Step 2 16k Exp 202412: 43.9 (#176)
| Benchmark | Hy3 | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Non-English | 1427 | 1290 |
| LMArena Chinese | 1496 | 1331 |
| LMArena Russian | 1435 | 1324 |
| LMArena French | 1461 | — |
| LMArena Korean | 1390 | — |
| LMArena Spanish | 1448 | — |
Instruction Following Hy3 leads
Hy3: 75.3 (#68), Step 2 16k Exp 202412: 68.1 (#187)
| Benchmark | Hy3 | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Instruction Following | 1425 | 1287 |
Long Context Hy3 leads
Hy3: 44.1 (#70), Step 2 16k Exp 202412: 39.7 (#165)
| Benchmark | Hy3 | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Longer Query | 1443 | 1307 |
Writing & Preference Hy3 leads
Hy3: 62.5 (#75), Step 2 16k Exp 202412: 52.5 (#168)
| Benchmark | Hy3 | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Text | 1442 | 1321 |
| LMArena Creative Writing | 1399 | 1328 |
| LMArena Multi-Turn | 1436 | 1292 |
Frequently asked questions
Is Hy3 better than Step 2 16k Exp 202412?
Hy3 is the stronger model overall, scoring 43.6 to 38.6 on the Noometry Index.
Is Hy3 or Step 2 16k Exp 202412 better for coding?
Hy3 scores higher on coding benchmarks: 46.6 versus 37.9 in the Noometry coding category.
How many benchmarks do Hy3 and Step 2 16k Exp 202412 share?
12 benchmarks have published results for both models. Hy3 has 17 scored results on Noometry and Step 2 16k Exp 202412 has 12.