Model comparison
Granite 4.0 Micro vs Step 3
Step 3 is the stronger model overall, scoring 39.9 to 28.8 on the Noometry Index.
Last verified . 0 shared benchmarks.
StepFunSummary
- The widest gap is in knowledge, where Step 3 leads 36.2 to 9.9.
Side by side
| Granite 4.0 Micro | Step 3 | |
|---|---|---|
| Provider | IBM | StepFun |
| Noometry Index | 28.8 | 39.9 |
| Released | 2025-10-02 | — |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 118K | — |
| Input $ / M tokens | $0.017 | — |
| Output $ / M tokens | $0.11 | — |
| Results tracked | 8 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Granite 4.0 Micro: —, Step 3: 39.5 (#144)
| Benchmark | Granite 4.0 Micro | Step 3 |
|---|---|---|
| LMArena Coding | — | 1367 |
Reasoning Step 3 leads
Granite 4.0 Micro: 18.5 (#261), Step 3: 27.6 (#102)
| Benchmark | Granite 4.0 Micro | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | — | 62.3% |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | — | 1355 |
Math Step 3 leads
Granite 4.0 Micro: 11.2 (#301), Step 3: 34.9 (#148)
| Benchmark | Granite 4.0 Micro | Step 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.8% | — |
| Omni-MATH | 20.9% | — |
| LMArena Math | — | 1366 |
Knowledge Step 3 leads
Granite 4.0 Micro: 9.9 (#299), Step 3: 36.2 (#161)
| Benchmark | Granite 4.0 Micro | Step 3 |
|---|---|---|
| GPQA Diamond | 28.3% | — |
| MMLU-Pro | 39.5% | — |
| GPQA (HELM) | 30.7% | — |
| LMArena Expert | — | 1333 |
Multimodal Not comparable
Granite 4.0 Micro: —, Step 3: 34.9 (#81)
| Benchmark | Granite 4.0 Micro | Step 3 |
|---|---|---|
| LMArena Vision | — | 1176 |
Multilingual Not comparable
Granite 4.0 Micro: —, Step 3: 46.5 (#154)
| Benchmark | Granite 4.0 Micro | Step 3 |
|---|---|---|
| LMArena Non-English | — | 1327 |
| LMArena Chinese | — | 1396 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1271 |
| LMArena Russian | — | 1331 |
| LMArena Spanish | — | 1372 |
Instruction Following Too close to call
Granite 4.0 Micro: 70.0 (#164), Step 3: 70.6 (#159)
| Benchmark | Granite 4.0 Micro | Step 3 |
|---|---|---|
| IFEval | 84.9% | — |
| LMArena Instruction Following | — | 1332 |
Long Context Not comparable
Granite 4.0 Micro: —, Step 3: 40.3 (#152)
| Benchmark | Granite 4.0 Micro | Step 3 |
|---|---|---|
| LMArena Longer Query | — | 1326 |
Writing & Preference Step 3 leads
Granite 4.0 Micro: 46.7 (#212), Step 3: 54.5 (#146)
| Benchmark | Granite 4.0 Micro | Step 3 |
|---|---|---|
| LMArena Text | — | 1351 |
| LMArena Creative Writing | — | 1322 |
| WildBench | 67% | — |
| LMArena Multi-Turn | — | 1340 |
Frequently asked questions
Is Granite 4.0 Micro better than Step 3?
Step 3 is the stronger model overall, scoring 39.9 to 28.8 on the Noometry Index.
How many benchmarks do Granite 4.0 Micro and Step 3 share?
0 benchmarks have published results for both models. Granite 4.0 Micro has 8 scored results on Noometry and Step 3 has 17.