Model comparison
DeepSeek Coder 6.7B vs Gemma 7B
Gemma 7B has enough public results to be ranked (#299); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.
Last verified . 7 shared benchmarks.
DeepSeek
GoogleSummary
- They share 7 benchmarks with published results for both. DeepSeek Coder 6.7B scores higher in 1 category and Gemma 7B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek Coder 6.7B leads 35.8 to 30.5.
Side by side
| DeepSeek Coder 6.7B | Gemma 7B | |
|---|---|---|
| Provider | DeepSeek | |
| Noometry Index | 37.6 | 30.0 |
| Released | 2023-11-02 | 2024-02-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek Coder 6.7B leads
DeepSeek Coder 6.7B: 35.8 (#219), Gemma 7B: 30.5 (#294)
| Benchmark | DeepSeek Coder 6.7B | Gemma 7B |
|---|---|---|
| HumanEval+ | 71.3% | 28.7% |
| MBPP+ | 65.6% | 43.4% |
| BigCodeBench Instruct | 35.5% | — |
| LMArena Coding | — | 1048 |
| BigCodeBench Complete | 43.8% | — |
Reasoning Not comparable
DeepSeek Coder 6.7B: —, Gemma 7B: 19.9 (#249)
| Benchmark | DeepSeek Coder 6.7B | Gemma 7B |
|---|---|---|
| Epoch Capabilities Index | 89.62 | 111.99 |
| WinoGrande | 57.6% | 79% |
| LMArena Hard Prompts | — | 1042 |
| Adversarial NLI | — | 48.7% |
| BIG-Bench Hard | — | 55.1% |
| HellaSwag | — | 82.2% |
| PIQA | — | 81.2% |
Math Not comparable
DeepSeek Coder 6.7B: —, Gemma 7B: 31.2 (#228)
| Benchmark | DeepSeek Coder 6.7B | Gemma 7B |
|---|---|---|
| GSM8K | 21.3% | 46.4% |
| LMArena Math | — | 1066 |
Knowledge Not comparable
DeepSeek Coder 6.7B: —, Gemma 7B: 27.3 (#252)
| Benchmark | DeepSeek Coder 6.7B | Gemma 7B |
|---|---|---|
| ARC (AI2) Challenge | 36.4% | 78.3% |
| MMLU | 36.4% | 66.1% |
| LMArena Expert | — | 1001 |
| BoolQ | — | 83.2% |
| OpenBookQA | — | 78.6% |
| TriviaQA | — | 72.3% |
Multilingual Not comparable
DeepSeek Coder 6.7B: —, Gemma 7B: 25.1 (#287)
| Benchmark | DeepSeek Coder 6.7B | Gemma 7B |
|---|---|---|
| LMArena Non-English | — | 999 |
| LMArena Chinese | — | 1035 |
| LMArena French | — | 1025 |
| LMArena Russian | — | 993 |
Instruction Following Not comparable
DeepSeek Coder 6.7B: —, Gemma 7B: 51.5 (#295)
| Benchmark | DeepSeek Coder 6.7B | Gemma 7B |
|---|---|---|
| LMArena Instruction Following | — | 1017 |
Long Context Not comparable
DeepSeek Coder 6.7B: —, Gemma 7B: 31.1 (#282)
| Benchmark | DeepSeek Coder 6.7B | Gemma 7B |
|---|---|---|
| LMArena Longer Query | — | 1022 |
Writing & Preference Not comparable
DeepSeek Coder 6.7B: —, Gemma 7B: 27.1 (#302)
| Benchmark | DeepSeek Coder 6.7B | Gemma 7B |
|---|---|---|
| LMArena Text | — | 1056 |
| LMArena Creative Writing | — | 1024 |
| LMArena Multi-Turn | — | 963 |
Frequently asked questions
Is DeepSeek Coder 6.7B better than Gemma 7B?
Gemma 7B has enough public results to be ranked (#299); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.
Is DeepSeek Coder 6.7B or Gemma 7B better for coding?
DeepSeek Coder 6.7B scores higher on coding benchmarks: 35.8 versus 30.5 in the Noometry coding category.
How many benchmarks do DeepSeek Coder 6.7B and Gemma 7B share?
7 benchmarks have published results for both models. DeepSeek Coder 6.7B has 9 scored results on Noometry and Gemma 7B has 27.