Model comparison
DeepSeek Coder 6.7B vs Deepseek Coder v2
Deepseek Coder v2 has enough public results to be ranked (#220); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.
Last verified . 7 shared benchmarks.
DeepSeekSummary
- They share 7 benchmarks with published results for both. DeepSeek Coder 6.7B scores higher in 0 categories and Deepseek Coder v2 in 1 category; one gap is clear of the uncertainty.
- The biggest single-benchmark swing is BigCodeBench Complete: 43.8% for DeepSeek Coder 6.7B and 59.7% for Deepseek Coder v2.
Side by side
| DeepSeek Coder 6.7B | Deepseek Coder v2 | |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| Noometry Index | 37.6 | 35.9 |
| Released | 2023-11-02 | 2024-06-17 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Deepseek Coder v2 leads
DeepSeek Coder 6.7B: 35.8 (#219), Deepseek Coder v2: 38.1 (#183)
| Benchmark | DeepSeek Coder 6.7B | Deepseek Coder v2 |
|---|---|---|
| BigCodeBench Instruct | 35.5% | 48.2% |
| BigCodeBench Complete | 43.8% | 59.7% |
| HumanEval+ | 71.3% | 82.3% |
| MBPP+ | 65.6% | 75.1% |
| LMArena Coding | — | 1251 |
Reasoning Not comparable
DeepSeek Coder 6.7B: —, Deepseek Coder v2: 23.6 (#176)
| Benchmark | DeepSeek Coder 6.7B | Deepseek Coder v2 |
|---|---|---|
| WinoGrande | 57.6% | 83.7% |
| LMArena Hard Prompts | — | 1207 |
| Epoch Capabilities Index | 89.62 | — |
Math Not comparable
DeepSeek Coder 6.7B: —, Deepseek Coder v2: 34.9 (#190)
| Benchmark | DeepSeek Coder 6.7B | Deepseek Coder v2 |
|---|---|---|
| GSM8K | 21.3% | 94.5% |
| LMArena Math | — | 1241 |
Knowledge Not comparable
DeepSeek Coder 6.7B: —, Deepseek Coder v2: 32.3 (#212)
| Benchmark | DeepSeek Coder 6.7B | Deepseek Coder v2 |
|---|---|---|
| ARC (AI2) Challenge | 36.4% | 64.3% |
| LMArena Expert | — | 1181 |
| MMLU | 36.4% | — |
Multilingual Not comparable
DeepSeek Coder 6.7B: —, Deepseek Coder v2: 36.3 (#240)
| Benchmark | DeepSeek Coder 6.7B | Deepseek Coder v2 |
|---|---|---|
| LMArena Non-English | — | 1182 |
| LMArena Chinese | — | 1201 |
| LMArena French | — | 1185 |
| LMArena German | — | 1164 |
| LMArena Japanese | — | 1126 |
| LMArena Korean | — | 1104 |
| LMArena Russian | — | 1188 |
| LMArena Spanish | — | 1153 |
Instruction Following Not comparable
DeepSeek Coder 6.7B: —, Deepseek Coder v2: 61.7 (#242)
| Benchmark | DeepSeek Coder 6.7B | Deepseek Coder v2 |
|---|---|---|
| LMArena Instruction Following | — | 1180 |
Long Context Not comparable
DeepSeek Coder 6.7B: —, Deepseek Coder v2: 37.0 (#224)
| Benchmark | DeepSeek Coder 6.7B | Deepseek Coder v2 |
|---|---|---|
| LMArena Longer Query | — | 1219 |
Writing & Preference Not comparable
DeepSeek Coder 6.7B: —, Deepseek Coder v2: 38.2 (#253)
| Benchmark | DeepSeek Coder 6.7B | Deepseek Coder v2 |
|---|---|---|
| LMArena Text | — | 1191 |
| LMArena Creative Writing | — | 1120 |
| LMArena Multi-Turn | — | 1177 |
Frequently asked questions
Is DeepSeek Coder 6.7B better than Deepseek Coder v2?
Deepseek Coder v2 has enough public results to be ranked (#220); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.
Is DeepSeek Coder 6.7B or Deepseek Coder v2 better for coding?
Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 35.8 in the Noometry coding category.
How many benchmarks do DeepSeek Coder 6.7B and Deepseek Coder v2 share?
7 benchmarks have published results for both models. DeepSeek Coder 6.7B has 9 scored results on Noometry and Deepseek Coder v2 has 24.