Model comparison
Deepseek Coder v2 vs Gemma 3n E4b IT
Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 35.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeek
GoogleSummary
- They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 2 categories and Gemma 3n E4b IT in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 3n E4b IT leads 50.1 to 38.2.
Side by side
| Deepseek Coder v2 | Gemma 3n E4b IT | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 35.9 | 37.3 |
| Released | 2024-06-17 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Deepseek Coder v2 leads
Deepseek Coder v2: 38.1 (#183), Gemma 3n E4b IT: 37.0 (#198)
| Benchmark | Deepseek Coder v2 | Gemma 3n E4b IT |
|---|---|---|
| LMArena Coding | 1251 | 1268 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Deepseek Coder v2 leads
Deepseek Coder v2: 23.6 (#176), Gemma 3n E4b IT: 19.9 (#247)
| Benchmark | Deepseek Coder v2 | Gemma 3n E4b IT |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1284 |
| Kagi LLM Benchmark | — | 31.5% |
| WinoGrande | 83.7% | — |
Math Too close to call
Deepseek Coder v2: 34.9 (#190), Gemma 3n E4b IT: 35.1 (#188)
| Benchmark | Deepseek Coder v2 | Gemma 3n E4b IT |
|---|---|---|
| LMArena Math | 1241 | 1251 |
| GSM8K | 94.5% | — |
Knowledge Gemma 3n E4b IT leads
Deepseek Coder v2: 32.3 (#212), Gemma 3n E4b IT: 34.2 (#198)
| Benchmark | Deepseek Coder v2 | Gemma 3n E4b IT |
|---|---|---|
| LMArena Expert | 1181 | 1246 |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Gemma 3n E4b IT leads
Deepseek Coder v2: 36.3 (#240), Gemma 3n E4b IT: 43.4 (#183)
| Benchmark | Deepseek Coder v2 | Gemma 3n E4b IT |
|---|---|---|
| LMArena Non-English | 1182 | 1285 |
| LMArena Chinese | 1201 | 1309 |
| LMArena French | 1185 | 1330 |
| LMArena German | 1164 | 1311 |
| LMArena Japanese | 1126 | 1272 |
| LMArena Korean | 1104 | 1259 |
| LMArena Russian | 1188 | 1288 |
| LMArena Spanish | 1153 | 1305 |
Instruction Following Gemma 3n E4b IT leads
Deepseek Coder v2: 61.7 (#242), Gemma 3n E4b IT: 66.1 (#210)
| Benchmark | Deepseek Coder v2 | Gemma 3n E4b IT |
|---|---|---|
| LMArena Instruction Following | 1180 | 1255 |
Long Context Gemma 3n E4b IT leads
Deepseek Coder v2: 37.0 (#224), Gemma 3n E4b IT: 38.7 (#191)
| Benchmark | Deepseek Coder v2 | Gemma 3n E4b IT |
|---|---|---|
| LMArena Longer Query | 1219 | 1276 |
Writing & Preference Gemma 3n E4b IT leads
Deepseek Coder v2: 38.2 (#253), Gemma 3n E4b IT: 50.1 (#186)
| Benchmark | Deepseek Coder v2 | Gemma 3n E4b IT |
|---|---|---|
| LMArena Text | 1191 | 1306 |
| LMArena Creative Writing | 1120 | 1287 |
| LMArena Multi-Turn | 1177 | 1276 |
Frequently asked questions
Is Deepseek Coder v2 better than Gemma 3n E4b IT?
Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or Gemma 3n E4b IT better for coding?
Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 37.0 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Gemma 3n E4b IT share?
17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Gemma 3n E4b IT has 18.