Model comparison
DeepSeek Coder 1.3B vs Phi-3.5-mini
Neither DeepSeek Coder 1.3B nor Phi-3.5-mini has enough public benchmark results to be ranked yet; the rows below show what has been published.
Last verified . 3 shared benchmarks.
DeepSeek
MicrosoftSummary
- They share 3 benchmarks with published results for both. DeepSeek Coder 1.3B scores higher in 0 categories and Phi-3.5-mini in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where Phi-3.5-mini leads 34.6 to 31.2.
- The biggest single-benchmark swing is BigCodeBench Instruct: 22.8% for DeepSeek Coder 1.3B and 32.8% for Phi-3.5-mini.
Side by side
| DeepSeek Coder 1.3B | Phi-3.5-mini | |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 35.0 | 36.9 |
| Released | 2023-11-02 | 2024-08-16 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Phi-3.5-mini leads
DeepSeek Coder 1.3B: 31.2 (#287), Phi-3.5-mini: 34.6 (#232)
| Benchmark | DeepSeek Coder 1.3B | Phi-3.5-mini |
|---|---|---|
| BigCodeBench Instruct | 22.8% | 32.8% |
| BigCodeBench Complete | 29.6% | 38.5% |
| HumanEval+ | 60.4% | — |
| MBPP+ | 54.8% | — |
Reasoning Not comparable
DeepSeek Coder 1.3B: —, Phi-3.5-mini: —
| Benchmark | DeepSeek Coder 1.3B | Phi-3.5-mini |
|---|---|---|
| Epoch Capabilities Index | 63.6 | — |
| PIQA | — | 81% |
| WinoGrande | 53.3% | — |
Math Not comparable
DeepSeek Coder 1.3B: —, Phi-3.5-mini: —
| Benchmark | DeepSeek Coder 1.3B | Phi-3.5-mini |
|---|---|---|
| GSM8K | 4.4% | 86.2% |
Knowledge Not comparable
DeepSeek Coder 1.3B: —, Phi-3.5-mini: —
| Benchmark | DeepSeek Coder 1.3B | Phi-3.5-mini |
|---|---|---|
| ARC (AI2) Challenge | 25.4% | — |
| BoolQ | — | 78% |
| MMLU | 25.8% | — |
Frequently asked questions
Is DeepSeek Coder 1.3B better than Phi-3.5-mini?
Neither DeepSeek Coder 1.3B nor Phi-3.5-mini has enough public benchmark results to be ranked yet; the rows below show what has been published.
Is DeepSeek Coder 1.3B or Phi-3.5-mini better for coding?
Phi-3.5-mini scores higher on coding benchmarks: 34.6 versus 31.2 in the Noometry coding category.
How many benchmarks do DeepSeek Coder 1.3B and Phi-3.5-mini share?
3 benchmarks have published results for both models. DeepSeek Coder 1.3B has 9 scored results on Noometry and Phi-3.5-mini has 5.