Model comparison
Granite 3.1 2b Instruct vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 33.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
StepFunSummary
- They share 12 benchmarks with published results for both. Granite 3.1 2b Instruct scores higher in 0 categories and Step 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3 leads 54.3 to 34.1.
Side by side
| Granite 3.1 2b Instruct | Step 3 | |
|---|---|---|
| Provider | IBM | StepFun |
| Noometry Index | 33.2 | 40.5 |
| Released | — | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 12 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Granite 3.1 2b Instruct: 33.4 (#257), Step 3: 40.1 (#147)
| Benchmark | Granite 3.1 2b Instruct | Step 3 |
|---|---|---|
| LMArena Coding | 1149 | 1367 |
Reasoning Step 3 leads
Granite 3.1 2b Instruct: 22.0 (#209), Step 3: 28.4 (#105)
| Benchmark | Granite 3.1 2b Instruct | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1138 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
Math Step 3 leads
Granite 3.1 2b Instruct: 33.1 (#206), Step 3: 37.6 (#148)
| Benchmark | Granite 3.1 2b Instruct | Step 3 |
|---|---|---|
| LMArena Math | 1159 | 1366 |
Knowledge Step 3 leads
Granite 3.1 2b Instruct: 30.8 (#224), Step 3: 36.8 (#164)
| Benchmark | Granite 3.1 2b Instruct | Step 3 |
|---|---|---|
| LMArena Expert | 1131 | 1333 |
Multimodal Not comparable
Granite 3.1 2b Instruct: —, Step 3: 35.5 (#86)
| Benchmark | Granite 3.1 2b Instruct | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Step 3 leads
Granite 3.1 2b Instruct: 29.1 (#269), Step 3: 46.3 (#159)
| Benchmark | Granite 3.1 2b Instruct | Step 3 |
|---|---|---|
| LMArena Non-English | 1068 | 1327 |
| LMArena Chinese | 1139 | 1397 |
| LMArena Russian | 1063 | 1331 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1269 |
| LMArena Spanish | — | 1371 |
Instruction Following Step 3 leads
Granite 3.1 2b Instruct: 57.7 (#264), Step 3: 70.4 (#164)
| Benchmark | Granite 3.1 2b Instruct | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1116 | 1332 |
Long Context Step 3 leads
Granite 3.1 2b Instruct: 35.0 (#244), Step 3: 40.3 (#157)
| Benchmark | Granite 3.1 2b Instruct | Step 3 |
|---|---|---|
| LMArena Longer Query | 1155 | 1326 |
Writing & Preference Step 3 leads
Granite 3.1 2b Instruct: 34.1 (#274), Step 3: 54.3 (#151)
| Benchmark | Granite 3.1 2b Instruct | Step 3 |
|---|---|---|
| LMArena Text | 1127 | 1350 |
| LMArena Creative Writing | 1116 | 1321 |
| LMArena Multi-Turn | 1099 | 1341 |
Frequently asked questions
Is Granite 3.1 2b Instruct better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 33.2 on the Noometry Index.
Is Granite 3.1 2b Instruct or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 33.4 in the Noometry coding category.
How many benchmarks do Granite 3.1 2b Instruct and Step 3 share?
12 benchmarks have published results for both models. Granite 3.1 2b Instruct has 12 scored results on Noometry and Step 3 has 17.