Model comparison
DeepSeek Coder 6.7B vs StarCoder 2 15B
Neither DeepSeek Coder 6.7B nor StarCoder 2 15B has enough public benchmark results to be ranked yet; the rows below show what has been published.
Last verified . 7 shared benchmarks.
DeepSeek
NVIDIASummary
- They share 7 benchmarks with published results for both. DeepSeek Coder 6.7B scores higher in 0 categories and StarCoder 2 15B in 1 category, but none of those gaps is larger than the uncertainty.
- The biggest single-benchmark swing is BigCodeBench Complete: 43.8% for DeepSeek Coder 6.7B and 38.4% for StarCoder 2 15B.
Side by side
| DeepSeek Coder 6.7B | StarCoder 2 15B | |
|---|---|---|
| Provider | DeepSeek | NVIDIA |
| Noometry Index | 37.6 | 38.1 |
| Released | 2023-11-02 | 2024-02-20 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek Coder 6.7B: 35.8 (#219), StarCoder 2 15B: 36.6
| Benchmark | DeepSeek Coder 6.7B | StarCoder 2 15B |
|---|---|---|
| BigCodeBench Complete | 43.8% | 38.4% |
| HumanEval+ | 71.3% | 37.8% |
| BigCodeBench Instruct | 35.5% | — |
| MBPP+ | 65.6% | — |
Reasoning Not comparable
DeepSeek Coder 6.7B: —, StarCoder 2 15B: —
| Benchmark | DeepSeek Coder 6.7B | StarCoder 2 15B |
|---|---|---|
| Epoch Capabilities Index | 89.62 | 105 |
| WinoGrande | 57.6% | 64.3% |
Math Not comparable
DeepSeek Coder 6.7B: —, StarCoder 2 15B: —
| Benchmark | DeepSeek Coder 6.7B | StarCoder 2 15B |
|---|---|---|
| GSM8K | 21.3% | 57.7% |
Knowledge Not comparable
DeepSeek Coder 6.7B: —, StarCoder 2 15B: —
| Benchmark | DeepSeek Coder 6.7B | StarCoder 2 15B |
|---|---|---|
| ARC (AI2) Challenge | 36.4% | 47.2% |
| MMLU | 36.4% | 64.1% |
Frequently asked questions
Is DeepSeek Coder 6.7B better than StarCoder 2 15B?
Neither DeepSeek Coder 6.7B nor StarCoder 2 15B has enough public benchmark results to be ranked yet; the rows below show what has been published.
Is DeepSeek Coder 6.7B or StarCoder 2 15B better for coding?
They score almost the same on coding (35.8 vs 36.6); test both on your own repository before choosing.
How many benchmarks do DeepSeek Coder 6.7B and StarCoder 2 15B share?
7 benchmarks have published results for both models. DeepSeek Coder 6.7B has 9 scored results on Noometry and StarCoder 2 15B has 7.