Model comparison
Gemma 3n E4b IT vs Step 2 16k Exp 202412
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 37.3 on the Noometry Index.
Last verified . 12 shared benchmarks.
Google
StepFunSummary
- They share 12 benchmarks with published results for both. Gemma 3n E4b IT scores higher in 0 categories and Step 2 16k Exp 202412 in 8 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 2 16k Exp 202412 leads 25.9 to 19.9.
- Gemma 3n E4b IT has downloadable open weights; the other is API-only.
Side by side
| Gemma 3n E4b IT | Step 2 16k Exp 202412 | |
|---|---|---|
| Provider | StepFun | |
| Noometry Index | 37.3 | 39.2 |
| Released | — | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 18 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 2 16k Exp 202412 leads
Gemma 3n E4b IT: 37.0 (#198), Step 2 16k Exp 202412: 38.5 (#174)
| Benchmark | Gemma 3n E4b IT | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Coding | 1268 | 1316 |
Reasoning Step 2 16k Exp 202412 leads
Gemma 3n E4b IT: 19.9 (#247), Step 2 16k Exp 202412: 25.9 (#142)
| Benchmark | Gemma 3n E4b IT | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Hard Prompts | 1284 | 1299 |
| Kagi LLM Benchmark | 31.5% | — |
Math Step 2 16k Exp 202412 leads
Gemma 3n E4b IT: 35.1 (#188), Step 2 16k Exp 202412: 36.3 (#169)
| Benchmark | Gemma 3n E4b IT | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Math | 1251 | 1304 |
Knowledge Too close to call
Gemma 3n E4b IT: 34.2 (#198), Step 2 16k Exp 202412: 35.2 (#187)
| Benchmark | Gemma 3n E4b IT | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Expert | 1246 | 1279 |
Multilingual Too close to call
Gemma 3n E4b IT: 43.4 (#183), Step 2 16k Exp 202412: 43.7 (#181)
| Benchmark | Gemma 3n E4b IT | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Non-English | 1285 | 1290 |
| LMArena Chinese | 1309 | 1331 |
| LMArena Russian | 1288 | 1324 |
| LMArena French | 1330 | — |
| LMArena German | 1311 | — |
| LMArena Japanese | 1272 | — |
| LMArena Korean | 1259 | — |
| LMArena Spanish | 1305 | — |
Instruction Following Step 2 16k Exp 202412 leads
Gemma 3n E4b IT: 66.1 (#210), Step 2 16k Exp 202412: 67.9 (#192)
| Benchmark | Gemma 3n E4b IT | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Instruction Following | 1255 | 1287 |
Long Context Too close to call
Gemma 3n E4b IT: 38.7 (#191), Step 2 16k Exp 202412: 39.7 (#170)
| Benchmark | Gemma 3n E4b IT | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Longer Query | 1276 | 1307 |
Writing & Preference Step 2 16k Exp 202412 leads
Gemma 3n E4b IT: 50.1 (#186), Step 2 16k Exp 202412: 52.3 (#173)
| Benchmark | Gemma 3n E4b IT | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Text | 1306 | 1321 |
| LMArena Creative Writing | 1287 | 1328 |
| LMArena Multi-Turn | 1276 | 1292 |
Frequently asked questions
Is Gemma 3n E4b IT better than Step 2 16k Exp 202412?
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 37.3 on the Noometry Index.
Is Gemma 3n E4b IT or Step 2 16k Exp 202412 better for coding?
Step 2 16k Exp 202412 scores higher on coding benchmarks: 38.5 versus 37.0 in the Noometry coding category.
How many benchmarks do Gemma 3n E4b IT and Step 2 16k Exp 202412 share?
12 benchmarks have published results for both models. Gemma 3n E4b IT has 18 scored results on Noometry and Step 2 16k Exp 202412 has 12.