Model comparison
Gemma 2B vs Gemma 3n E4b IT
Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 29.6 on the Noometry Index.
Last verified . 11 shared benchmarks.
GoogleSummary
- They share 11 benchmarks with published results for both. Gemma 2B scores higher in 0 categories and Gemma 3n E4b IT in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 3n E4b IT leads 50.1 to 24.0.
Side by side
| Gemma 2B | Gemma 3n E4b IT | |
|---|---|---|
| Provider | ||
| Noometry Index | 29.6 | 37.3 |
| Released | 2024-02-21 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 23 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3n E4b IT leads
Gemma 2B: 29.4 (#305), Gemma 3n E4b IT: 37.0 (#198)
| Benchmark | Gemma 2B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Coding | 1010 | 1268 |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Reasoning Gemma 3n E4b IT leads
Gemma 2B: 18.8 (#275), Gemma 3n E4b IT: 19.9 (#247)
| Benchmark | Gemma 2B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Hard Prompts | 989 | 1284 |
| Kagi LLM Benchmark | — | 31.5% |
| BIG-Bench Hard | 35.2% | — |
| Epoch Capabilities Index | 94.2 | — |
| HellaSwag | 71.4% | — |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |
Math Gemma 3n E4b IT leads
Gemma 2B: 30.0 (#239), Gemma 3n E4b IT: 35.1 (#188)
| Benchmark | Gemma 2B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Math | 1009 | 1251 |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, Gemma 3n E4b IT: 34.2 (#198)
| Benchmark | Gemma 2B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Expert | — | 1246 |
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| MMLU | 42.3% | — |
| TriviaQA | 53.2% | — |
Multilingual Gemma 3n E4b IT leads
Gemma 2B: 23.0 (#294), Gemma 3n E4b IT: 43.4 (#183)
| Benchmark | Gemma 2B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Non-English | 958 | 1285 |
| LMArena Chinese | 986 | 1309 |
| LMArena Russian | 937 | 1288 |
| LMArena French | — | 1330 |
| LMArena German | — | 1311 |
| LMArena Japanese | — | 1272 |
| LMArena Korean | — | 1259 |
| LMArena Spanish | — | 1305 |
Instruction Following Gemma 3n E4b IT leads
Gemma 2B: 48.5 (#302), Gemma 3n E4b IT: 66.1 (#210)
| Benchmark | Gemma 2B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Instruction Following | 970 | 1255 |
Long Context Gemma 3n E4b IT leads
Gemma 2B: 29.9 (#291), Gemma 3n E4b IT: 38.7 (#191)
| Benchmark | Gemma 2B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Longer Query | 981 | 1276 |
Writing & Preference Gemma 3n E4b IT leads
Gemma 2B: 24.0 (#308), Gemma 3n E4b IT: 50.1 (#186)
| Benchmark | Gemma 2B | Gemma 3n E4b IT |
|---|---|---|
| LMArena Text | 1002 | 1306 |
| LMArena Creative Writing | 987 | 1287 |
| LMArena Multi-Turn | 945 | 1276 |
Frequently asked questions
Is Gemma 2B better than Gemma 3n E4b IT?
Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 29.6 on the Noometry Index.
Is Gemma 2B or Gemma 3n E4b IT better for coding?
Gemma 3n E4b IT scores higher on coding benchmarks: 37.0 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2B and Gemma 3n E4b IT share?
11 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Gemma 3n E4b IT has 18.