Model comparison
Granite 4.2 30b vs Step 3
Granite 4.2 30b is the stronger model overall, scoring 41.8 to 40.5 on the Noometry Index.
Last verified . 11 shared benchmarks.
StepFunSummary
- They share 11 benchmarks with published results for both. Granite 4.2 30b scores higher in 5 categories and Step 3 in 2 categories; 2 gaps are clear of the uncertainty.
Side by side
| Granite 4.2 30b | Step 3 | |
|---|---|---|
| Provider | IBM | StepFun |
| Noometry Index | 41.8 | 40.5 |
| Released | — | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 11 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Granite 4.2 30b: 41.0 (#126), Step 3: 40.1 (#147)
| Benchmark | Granite 4.2 30b | Step 3 |
|---|---|---|
| LMArena Coding | 1396 | 1367 |
Reasoning Too close to call
Granite 4.2 30b: 27.8 (#112), Step 3: 28.4 (#105)
| Benchmark | Granite 4.2 30b | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1374 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
Math Not comparable
Granite 4.2 30b: —, Step 3: 37.6 (#148)
| Benchmark | Granite 4.2 30b | Step 3 |
|---|---|---|
| LMArena Math | — | 1366 |
Knowledge Granite 4.2 30b leads
Granite 4.2 30b: 39.1 (#138), Step 3: 36.8 (#164)
| Benchmark | Granite 4.2 30b | Step 3 |
|---|---|---|
| LMArena Expert | 1406 | 1333 |
Multimodal Not comparable
Granite 4.2 30b: —, Step 3: 35.5 (#86)
| Benchmark | Granite 4.2 30b | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Too close to call
Granite 4.2 30b: 47.3 (#151), Step 3: 46.3 (#159)
| Benchmark | Granite 4.2 30b | Step 3 |
|---|---|---|
| LMArena Non-English | 1340 | 1327 |
| LMArena Chinese | 1414 | 1397 |
| LMArena Russian | 1343 | 1331 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1269 |
| LMArena Spanish | — | 1371 |
Instruction Following Too close to call
Granite 4.2 30b: 71.2 (#155), Step 3: 70.4 (#164)
| Benchmark | Granite 4.2 30b | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1347 | 1332 |
Long Context Granite 4.2 30b leads
Granite 4.2 30b: 41.4 (#140), Step 3: 40.3 (#157)
| Benchmark | Granite 4.2 30b | Step 3 |
|---|---|---|
| LMArena Longer Query | 1359 | 1326 |
Writing & Preference Too close to call
Granite 4.2 30b: 53.8 (#156), Step 3: 54.3 (#151)
| Benchmark | Granite 4.2 30b | Step 3 |
|---|---|---|
| LMArena Text | 1361 | 1350 |
| LMArena Creative Writing | 1288 | 1321 |
| LMArena Multi-Turn | 1339 | 1341 |
Frequently asked questions
Is Granite 4.2 30b better than Step 3?
Granite 4.2 30b is the stronger model overall, scoring 41.8 to 40.5 on the Noometry Index.
Is Granite 4.2 30b or Step 3 better for coding?
They score almost the same on coding (41.0 vs 40.1); test both on your own repository before choosing.
How many benchmarks do Granite 4.2 30b and Step 3 share?
11 benchmarks have published results for both models. Granite 4.2 30b has 11 scored results on Noometry and Step 3 has 17.