Model comparison
Granite 4.2 3b vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 39.4 on the Noometry Index.
Last verified . 11 shared benchmarks.
StepFunSummary
- They share 11 benchmarks with published results for both. Granite 4.2 3b scores higher in 0 categories and Step 3 in 7 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3 leads 54.3 to 47.2.
Side by side
| Granite 4.2 3b | Step 3 | |
|---|---|---|
| Provider | IBM | StepFun |
| Noometry Index | 39.4 | 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 3b: 40.0 (#151), Step 3: 40.1 (#147)
| Benchmark | Granite 4.2 3b | Step 3 |
|---|---|---|
| LMArena Coding | 1361 | 1367 |
Reasoning Step 3 leads
Granite 4.2 3b: 26.0 (#138), Step 3: 28.4 (#105)
| Benchmark | Granite 4.2 3b | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1306 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
Math Not comparable
Granite 4.2 3b: —, Step 3: 37.6 (#148)
| Benchmark | Granite 4.2 3b | Step 3 |
|---|---|---|
| LMArena Math | — | 1366 |
Knowledge Too close to call
Granite 4.2 3b: 36.3 (#171), Step 3: 36.8 (#164)
| Benchmark | Granite 4.2 3b | Step 3 |
|---|---|---|
| LMArena Expert | 1315 | 1333 |
Multimodal Not comparable
Granite 4.2 3b: —, Step 3: 35.5 (#86)
| Benchmark | Granite 4.2 3b | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Step 3 leads
Granite 4.2 3b: 42.1 (#198), Step 3: 46.3 (#159)
| Benchmark | Granite 4.2 3b | Step 3 |
|---|---|---|
| LMArena Non-English | 1268 | 1327 |
| LMArena Chinese | 1269 | 1397 |
| LMArena Russian | 1249 | 1331 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1269 |
| LMArena Spanish | — | 1371 |
Instruction Following Step 3 leads
Granite 4.2 3b: 67.1 (#200), Step 3: 70.4 (#164)
| Benchmark | Granite 4.2 3b | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1273 | 1332 |
Long Context Step 3 leads
Granite 4.2 3b: 39.2 (#185), Step 3: 40.3 (#157)
| Benchmark | Granite 4.2 3b | Step 3 |
|---|---|---|
| LMArena Longer Query | 1291 | 1326 |
Writing & Preference Step 3 leads
Granite 4.2 3b: 47.2 (#212), Step 3: 54.3 (#151)
| Benchmark | Granite 4.2 3b | Step 3 |
|---|---|---|
| LMArena Text | 1293 | 1350 |
| LMArena Creative Writing | 1205 | 1321 |
| LMArena Multi-Turn | 1290 | 1341 |
Frequently asked questions
Is Granite 4.2 3b better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 39.4 on the Noometry Index.
Is Granite 4.2 3b or Step 3 better for coding?
They score almost the same on coding (40.0 vs 40.1); test both on your own repository before choosing.
How many benchmarks do Granite 4.2 3b and Step 3 share?
11 benchmarks have published results for both models. Granite 4.2 3b has 11 scored results on Noometry and Step 3 has 17.