Model comparison
Deepseek Coder v2 vs Gemma 2B
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 29.6 on the Noometry Index.
Last verified . 16 shared benchmarks.
DeepSeek
GoogleSummary
- They share 16 benchmarks with published results for both. Deepseek Coder v2 scores higher in 7 categories and Gemma 2B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Deepseek Coder v2 leads 38.2 to 24.0.
Side by side
| Deepseek Coder v2 | Gemma 2B | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 35.9 | 29.6 |
| Released | 2024-06-17 | 2024-02-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 23 |
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 2B: 29.4 (#305)
| Benchmark | Deepseek Coder v2 | Gemma 2B |
|---|---|---|
| LMArena Coding | 1251 | 1010 |
| HumanEval+ | 82.3% | 20.7% |
| MBPP+ | 75.1% | 34.1% |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
Reasoning Deepseek Coder v2 leads
Deepseek Coder v2: 23.6 (#176), Gemma 2B: 18.8 (#275)
| Benchmark | Deepseek Coder v2 | Gemma 2B |
|---|---|---|
| LMArena Hard Prompts | 1207 | 989 |
| WinoGrande | 83.7% | 65.4% |
| BIG-Bench Hard | — | 35.2% |
| Epoch Capabilities Index | — | 94.2 |
| HellaSwag | — | 71.4% |
| PIQA | — | 77.3% |
Math Deepseek Coder v2 leads
Deepseek Coder v2: 34.9 (#190), Gemma 2B: 30.0 (#239)
| Benchmark | Deepseek Coder v2 | Gemma 2B |
|---|---|---|
| LMArena Math | 1241 | 1009 |
| GSM8K | 94.5% | 17.7% |
Knowledge Not comparable
Deepseek Coder v2: 32.3 (#212), Gemma 2B: —
| Benchmark | Deepseek Coder v2 | Gemma 2B |
|---|---|---|
| ARC (AI2) Challenge | 64.3% | 42.1% |
| LMArena Expert | 1181 | — |
| BoolQ | — | 69.4% |
| MMLU | — | 42.3% |
| TriviaQA | — | 53.2% |
Multilingual Deepseek Coder v2 leads
Deepseek Coder v2: 36.3 (#240), Gemma 2B: 23.0 (#294)
| Benchmark | Deepseek Coder v2 | Gemma 2B |
|---|---|---|
| LMArena Non-English | 1182 | 958 |
| LMArena Chinese | 1201 | 986 |
| LMArena Russian | 1188 | 937 |
| LMArena French | 1185 | — |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Spanish | 1153 | — |
Instruction Following Deepseek Coder v2 leads
Deepseek Coder v2: 61.7 (#242), Gemma 2B: 48.5 (#302)
| Benchmark | Deepseek Coder v2 | Gemma 2B |
|---|---|---|
| LMArena Instruction Following | 1180 | 970 |
Long Context Deepseek Coder v2 leads
Deepseek Coder v2: 37.0 (#224), Gemma 2B: 29.9 (#291)
| Benchmark | Deepseek Coder v2 | Gemma 2B |
|---|---|---|
| LMArena Longer Query | 1219 | 981 |
Writing & Preference Deepseek Coder v2 leads
Deepseek Coder v2: 38.2 (#253), Gemma 2B: 24.0 (#308)
| Benchmark | Deepseek Coder v2 | Gemma 2B |
|---|---|---|
| LMArena Text | 1191 | 1002 |
| LMArena Creative Writing | 1120 | 987 |
| LMArena Multi-Turn | 1177 | 945 |
Frequently asked questions
Is Deepseek Coder v2 better than Gemma 2B?
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 29.6 on the Noometry Index.
Is Deepseek Coder v2 or Gemma 2B better for coding?
Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 29.4 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Gemma 2B share?
16 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Gemma 2B has 23.