Model comparison
Granite 4.2 30b vs Hy3
Hy3 is the stronger model overall, scoring 43.6 to 41.4 on the Noometry Index.
Last verified . 11 shared benchmarks.
TencentSummary
- They share 11 benchmarks with published results for both. Granite 4.2 30b scores higher in 1 category and Hy3 in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hy3 leads 62.5 to 54.3.
Side by side
| Granite 4.2 30b | Hy3 | |
|---|---|---|
| Provider | IBM | Tencent |
| Noometry Index | 41.4 | 43.6 |
| Released | — | 2026-07-06 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.13 |
| Output $ / M tokens | — | $0.53 |
| Results tracked | 11 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Granite 4.2 30b: 40.4 (#127), Hy3: 46.6 (#60)
| Benchmark | Granite 4.2 30b | Hy3 |
|---|---|---|
| LMArena Coding | 1394 | 1465 |
| LMArena WebDev | — | 1509 |
Reasoning Granite 4.2 30b leads
Granite 4.2 30b: 26.7 (#114), Hy3: 25.0 (#134)
| Benchmark | Granite 4.2 30b | Hy3 |
|---|---|---|
| LMArena Hard Prompts | 1375 | 1449 |
| NYT Connections (extended) | — | 41.2% |
Math Not comparable
Granite 4.2 30b: —, Hy3: 37.4 (#98)
| Benchmark | Granite 4.2 30b | Hy3 |
|---|---|---|
| LMArena Math | — | 1475 |
Knowledge Hy3 leads
Granite 4.2 30b: 38.5 (#134), Hy3: 40.2 (#108)
| Benchmark | Granite 4.2 30b | Hy3 |
|---|---|---|
| LMArena Expert | 1405 | 1461 |
Multilingual Hy3 leads
Granite 4.2 30b: 47.4 (#146), Hy3: 53.7 (#60)
| Benchmark | Granite 4.2 30b | Hy3 |
|---|---|---|
| LMArena Non-English | 1340 | 1427 |
| LMArena Chinese | 1415 | 1496 |
| LMArena Russian | 1342 | 1435 |
| LMArena French | — | 1461 |
| LMArena Korean | — | 1390 |
| LMArena Spanish | — | 1448 |
Instruction Following Hy3 leads
Granite 4.2 30b: 71.3 (#150), Hy3: 75.3 (#68)
| Benchmark | Granite 4.2 30b | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1346 | 1425 |
Long Context Hy3 leads
Granite 4.2 30b: 41.4 (#135), Hy3: 44.1 (#70)
| Benchmark | Granite 4.2 30b | Hy3 |
|---|---|---|
| LMArena Longer Query | 1359 | 1443 |
Writing & Preference Hy3 leads
Granite 4.2 30b: 54.3 (#147), Hy3: 62.5 (#75)
| Benchmark | Granite 4.2 30b | Hy3 |
|---|---|---|
| LMArena Text | 1363 | 1442 |
| LMArena Creative Writing | 1294 | 1399 |
| LMArena Multi-Turn | 1340 | 1436 |
Frequently asked questions
Is Granite 4.2 30b better than Hy3?
Hy3 is the stronger model overall, scoring 43.6 to 41.4 on the Noometry Index.
Is Granite 4.2 30b or Hy3 better for coding?
Hy3 scores higher on coding benchmarks: 46.6 versus 40.4 in the Noometry coding category.
How many benchmarks do Granite 4.2 30b and Hy3 share?
11 benchmarks have published results for both models. Granite 4.2 30b has 11 scored results on Noometry and Hy3 has 17.