Model comparison
Granite 4.1 8b vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 43.8 to 36.8 on the Noometry Index.
Last verified . 1 shared benchmarks.
StepFunSummary
- They share 1 benchmark with published results for both. Granite 4.1 8b scores higher in 0 categories and Step 5 Preview in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where Step 5 Preview leads 50.6 to 29.9.
- Granite 4.1 8b has downloadable open weights; the other is API-only.
Side by side
| Granite 4.1 8b | Step 5 Preview | |
|---|---|---|
| Provider | IBM | StepFun |
| Noometry Index | 36.8 | 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 | 13 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Granite 4.1 8b: 29.9 (#291), Step 5 Preview: 50.6 (#40)
| Benchmark | Granite 4.1 8b | Step 5 Preview |
|---|---|---|
| LMArena WebDev | 1190 | 1569 |
| SciCode | — | 58.9% |
| LMArena Coding | 1313 | — |
Reasoning Step 5 Preview leads
Granite 4.1 8b: 24.6 (#142), Step 5 Preview: 38.0 (#58)
| Benchmark | Granite 4.1 8b | Step 5 Preview |
|---|---|---|
| CritPt | — | 20.9% |
| LMArena Hard Prompts | 1294 | — |
Math Not comparable
Granite 4.1 8b: 33.8 (#167), Step 5 Preview: —
| Benchmark | Granite 4.1 8b | Step 5 Preview |
|---|---|---|
| LMArena Math | 1311 | — |
Knowledge Not comparable
Granite 4.1 8b: 35.5 (#171), Step 5 Preview: —
| Benchmark | Granite 4.1 8b | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1310 | — |
Multilingual Not comparable
Granite 4.1 8b: 41.8 (#199), Step 5 Preview: —
| Benchmark | Granite 4.1 8b | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1261 | — |
| LMArena Chinese | 1335 | — |
| LMArena Russian | 1238 | — |
Instruction Following Not comparable
Granite 4.1 8b: 67.0 (#198), Step 5 Preview: —
| Benchmark | Granite 4.1 8b | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1268 | — |
Long Context Not comparable
Granite 4.1 8b: 38.7 (#188), Step 5 Preview: —
| Benchmark | Granite 4.1 8b | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1275 | — |
Writing & Preference Not comparable
Granite 4.1 8b: 48.3 (#199), Step 5 Preview: —
| Benchmark | Granite 4.1 8b | Step 5 Preview |
|---|---|---|
| LMArena Text | 1291 | — |
| LMArena Creative Writing | 1249 | — |
| LMArena Multi-Turn | 1269 | — |
Frequently asked questions
Is Granite 4.1 8b better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 43.8 to 36.8 on the Noometry Index.
Is Granite 4.1 8b or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 50.6 versus 29.9 in the Noometry coding category.
How many benchmarks do Granite 4.1 8b and Step 5 Preview share?
1 benchmark has published results for both models. Granite 4.1 8b has 13 scored results on Noometry and Step 5 Preview has 3.