Model comparison
Granite 4.2 30b vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 43.8 to 41.4 on the Noometry Index.
Last verified . 0 shared benchmarks.
StepFunSummary
- The widest gap is in reasoning, where Step 5 Preview leads 38.0 to 26.7.
- Granite 4.2 30b has downloadable open weights; the other is API-only.
Side by side
| Granite 4.2 30b | Step 5 Preview | |
|---|---|---|
| Provider | IBM | StepFun |
| Noometry Index | 41.4 | 43.8 |
| Released | — | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | — | 1.02M |
| Max output | — | 66K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $2.70 |
| Results tracked | 11 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Granite 4.2 30b: 40.4 (#127), Step 5 Preview: 50.6 (#40)
| Benchmark | Granite 4.2 30b | Step 5 Preview |
|---|---|---|
| LMArena WebDev | — | 1569 |
| SciCode | — | 58.9% |
| LMArena Coding | 1394 | — |
Reasoning Step 5 Preview leads
Granite 4.2 30b: 26.7 (#114), Step 5 Preview: 38.0 (#58)
| Benchmark | Granite 4.2 30b | Step 5 Preview |
|---|---|---|
| CritPt | — | 20.9% |
| LMArena Hard Prompts | 1375 | — |
Knowledge Not comparable
Granite 4.2 30b: 38.5 (#134), Step 5 Preview: —
| Benchmark | Granite 4.2 30b | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1405 | — |
Multilingual Not comparable
Granite 4.2 30b: 47.4 (#146), Step 5 Preview: —
| Benchmark | Granite 4.2 30b | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1340 | — |
| LMArena Chinese | 1415 | — |
| LMArena Russian | 1342 | — |
Instruction Following Not comparable
Granite 4.2 30b: 71.3 (#150), Step 5 Preview: —
| Benchmark | Granite 4.2 30b | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1346 | — |
Long Context Not comparable
Granite 4.2 30b: 41.4 (#135), Step 5 Preview: —
| Benchmark | Granite 4.2 30b | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1359 | — |
Writing & Preference Not comparable
Granite 4.2 30b: 54.3 (#147), Step 5 Preview: —
| Benchmark | Granite 4.2 30b | Step 5 Preview |
|---|---|---|
| LMArena Text | 1363 | — |
| LMArena Creative Writing | 1294 | — |
| LMArena Multi-Turn | 1340 | — |
Frequently asked questions
Is Granite 4.2 30b better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 43.8 to 41.4 on the Noometry Index.
Is Granite 4.2 30b or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 50.6 versus 40.4 in the Noometry coding category.
How many benchmarks do Granite 4.2 30b and Step 5 Preview share?
0 benchmarks have published results for both models. Granite 4.2 30b has 11 scored results on Noometry and Step 5 Preview has 3.