Model comparison
Gemma 3n E4b IT vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 37.3 on the Noometry Index.
Last verified . 16 shared benchmarks.
Google
StepFunSummary
- They share 16 benchmarks with published results for both. Gemma 3n E4b IT scores higher in 0 categories and Step 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 3 leads 28.4 to 19.9.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 31.5% for Gemma 3n E4b IT and 62.3% for Step 3.
Side by side
| Gemma 3n E4b IT | Step 3 | |
|---|---|---|
| Provider | StepFun | |
| Noometry Index | 37.3 | 40.5 |
| Released | — | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 18 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Gemma 3n E4b IT: 37.0 (#198), Step 3: 40.1 (#147)
| Benchmark | Gemma 3n E4b IT | Step 3 |
|---|---|---|
| LMArena Coding | 1268 | 1367 |
Reasoning Step 3 leads
Gemma 3n E4b IT: 19.9 (#247), Step 3: 28.4 (#105)
| Benchmark | Gemma 3n E4b IT | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | 31.5% | 62.3% |
| LMArena Hard Prompts | 1284 | 1355 |
Math Step 3 leads
Gemma 3n E4b IT: 35.1 (#188), Step 3: 37.6 (#148)
| Benchmark | Gemma 3n E4b IT | Step 3 |
|---|---|---|
| LMArena Math | 1251 | 1366 |
Knowledge Step 3 leads
Gemma 3n E4b IT: 34.2 (#198), Step 3: 36.8 (#164)
| Benchmark | Gemma 3n E4b IT | Step 3 |
|---|---|---|
| LMArena Expert | 1246 | 1333 |
Multimodal Not comparable
Gemma 3n E4b IT: —, Step 3: 35.5 (#86)
| Benchmark | Gemma 3n E4b IT | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Step 3 leads
Gemma 3n E4b IT: 43.4 (#183), Step 3: 46.3 (#159)
| Benchmark | Gemma 3n E4b IT | Step 3 |
|---|---|---|
| LMArena Non-English | 1285 | 1327 |
| LMArena Chinese | 1309 | 1397 |
| LMArena German | 1311 | 1371 |
| LMArena Korean | 1259 | 1269 |
| LMArena Russian | 1288 | 1331 |
| LMArena Spanish | 1305 | 1371 |
| LMArena French | 1330 | — |
| LMArena Japanese | 1272 | — |
Instruction Following Step 3 leads
Gemma 3n E4b IT: 66.1 (#210), Step 3: 70.4 (#164)
| Benchmark | Gemma 3n E4b IT | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1255 | 1332 |
Long Context Step 3 leads
Gemma 3n E4b IT: 38.7 (#191), Step 3: 40.3 (#157)
| Benchmark | Gemma 3n E4b IT | Step 3 |
|---|---|---|
| LMArena Longer Query | 1276 | 1326 |
Writing & Preference Step 3 leads
Gemma 3n E4b IT: 50.1 (#186), Step 3: 54.3 (#151)
| Benchmark | Gemma 3n E4b IT | Step 3 |
|---|---|---|
| LMArena Text | 1306 | 1350 |
| LMArena Creative Writing | 1287 | 1321 |
| LMArena Multi-Turn | 1276 | 1341 |
Frequently asked questions
Is Gemma 3n E4b IT better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 37.3 on the Noometry Index.
Is Gemma 3n E4b IT or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 37.0 in the Noometry coding category.
How many benchmarks do Gemma 3n E4b IT and Step 3 share?
16 benchmarks have published results for both models. Gemma 3n E4b IT has 18 scored results on Noometry and Step 3 has 17.