Model comparison
Granite 4.1 8b vs Step 2 16k Exp 202412
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 37.4 on the Noometry Index.
Last verified . 12 shared benchmarks.
StepFunSummary
- They share 12 benchmarks with published results for both. Granite 4.1 8b scores higher in 2 categories and Step 2 16k Exp 202412 in 6 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in coding, where Step 2 16k Exp 202412 leads 38.5 to 30.1.
- Granite 4.1 8b has downloadable open weights; the other is API-only.
Side by side
| Granite 4.1 8b | Step 2 16k Exp 202412 | |
|---|---|---|
| Provider | IBM | StepFun |
| Noometry Index | 37.4 | 39.2 |
| Released | — | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 13 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 2 16k Exp 202412 leads
Granite 4.1 8b: 30.1 (#297), Step 2 16k Exp 202412: 38.5 (#174)
| Benchmark | Granite 4.1 8b | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Coding | 1312 | 1316 |
| LMArena WebDev | 1192 | — |
Reasoning Too close to call
Granite 4.1 8b: 25.7 (#143), Step 2 16k Exp 202412: 25.9 (#142)
| Benchmark | Granite 4.1 8b | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Hard Prompts | 1293 | 1299 |
Math Too close to call
Granite 4.1 8b: 36.4 (#166), Step 2 16k Exp 202412: 36.3 (#169)
| Benchmark | Granite 4.1 8b | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Math | 1312 | 1304 |
Knowledge Too close to call
Granite 4.1 8b: 36.1 (#174), Step 2 16k Exp 202412: 35.2 (#187)
| Benchmark | Granite 4.1 8b | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Expert | 1309 | 1279 |
Multilingual Step 2 16k Exp 202412 leads
Granite 4.1 8b: 41.7 (#204), Step 2 16k Exp 202412: 43.7 (#181)
| Benchmark | Granite 4.1 8b | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Non-English | 1261 | 1290 |
| LMArena Chinese | 1337 | 1331 |
| LMArena Russian | 1240 | 1324 |
Instruction Following Step 2 16k Exp 202412 leads
Granite 4.1 8b: 66.9 (#203), Step 2 16k Exp 202412: 67.9 (#192)
| Benchmark | Granite 4.1 8b | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Instruction Following | 1269 | 1287 |
Long Context Step 2 16k Exp 202412 leads
Granite 4.1 8b: 38.7 (#193), Step 2 16k Exp 202412: 39.7 (#170)
| Benchmark | Granite 4.1 8b | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Longer Query | 1275 | 1307 |
Writing & Preference Step 2 16k Exp 202412 leads
Granite 4.1 8b: 48.1 (#204), Step 2 16k Exp 202412: 52.3 (#173)
| Benchmark | Granite 4.1 8b | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Text | 1290 | 1321 |
| LMArena Creative Writing | 1251 | 1328 |
| LMArena Multi-Turn | 1268 | 1292 |
Frequently asked questions
Is Granite 4.1 8b better than Step 2 16k Exp 202412?
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 37.4 on the Noometry Index.
Is Granite 4.1 8b or Step 2 16k Exp 202412 better for coding?
Step 2 16k Exp 202412 scores higher on coding benchmarks: 38.5 versus 30.1 in the Noometry coding category.
How many benchmarks do Granite 4.1 8b and Step 2 16k Exp 202412 share?
12 benchmarks have published results for both models. Granite 4.1 8b has 13 scored results on Noometry and Step 2 16k Exp 202412 has 12.