Model comparison
DeepSeek Coder 1.3B vs DeepSeek Coder 6.7B
Neither DeepSeek Coder 1.3B nor DeepSeek Coder 6.7B has enough public benchmark results to be ranked yet; the rows below show what has been published.
Last verified . 9 shared benchmarks.
DeepSeekSummary
- They share 9 benchmarks with published results for both. DeepSeek Coder 1.3B scores higher in 0 categories and DeepSeek Coder 6.7B in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek Coder 6.7B leads 35.2 to 30.7.
- The biggest single-benchmark swing is BigCodeBench Complete: 29.6% for DeepSeek Coder 1.3B and 43.8% for DeepSeek Coder 6.7B.
Side by side
| DeepSeek Coder 1.3B | DeepSeek Coder 6.7B | |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| Noometry Index | 34.5 | 37.1 |
| Released | 2023-11-02 | 2023-11-02 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek Coder 6.7B leads
DeepSeek Coder 1.3B: 30.7 (#282), DeepSeek Coder 6.7B: 35.2 (#216)
| Benchmark | DeepSeek Coder 1.3B | DeepSeek Coder 6.7B |
|---|---|---|
| BigCodeBench Instruct | 22.8% | 35.5% |
| BigCodeBench Complete | 29.6% | 43.8% |
| HumanEval+ | 60.4% | 71.3% |
| MBPP+ | 54.8% | 65.6% |
Reasoning Not comparable
DeepSeek Coder 1.3B: —, DeepSeek Coder 6.7B: —
| Benchmark | DeepSeek Coder 1.3B | DeepSeek Coder 6.7B |
|---|---|---|
| Epoch Capabilities Index | 62.18 | 88.88 |
| WinoGrande | 53.3% | 57.6% |
Math Not comparable
DeepSeek Coder 1.3B: —, DeepSeek Coder 6.7B: —
| Benchmark | DeepSeek Coder 1.3B | DeepSeek Coder 6.7B |
|---|---|---|
| GSM8K | 4.4% | 21.3% |
Knowledge Not comparable
DeepSeek Coder 1.3B: —, DeepSeek Coder 6.7B: —
| Benchmark | DeepSeek Coder 1.3B | DeepSeek Coder 6.7B |
|---|---|---|
| ARC (AI2) Challenge | 25.4% | 36.4% |
| MMLU | 25.8% | 36.4% |
Frequently asked questions
Is DeepSeek Coder 1.3B better than DeepSeek Coder 6.7B?
Neither DeepSeek Coder 1.3B nor DeepSeek Coder 6.7B has enough public benchmark results to be ranked yet; the rows below show what has been published.
Is DeepSeek Coder 1.3B or DeepSeek Coder 6.7B better for coding?
DeepSeek Coder 6.7B scores higher on coding benchmarks: 35.2 versus 30.7 in the Noometry coding category.
How many benchmarks do DeepSeek Coder 1.3B and DeepSeek Coder 6.7B share?
9 benchmarks have published results for both models. DeepSeek Coder 1.3B has 9 scored results on Noometry and DeepSeek Coder 6.7B has 9.