Model comparison
DeepSeek Coder 33B vs Phi-2
Neither DeepSeek Coder 33B nor Phi-2 has enough public benchmark results to be ranked yet; the rows below show what has been published.
Last verified . 6 shared benchmarks.
DeepSeek
MicrosoftSummary
- They share 6 benchmarks with published results for both.
Side by side
| DeepSeek Coder 33B | Phi-2 | |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 38.3 | — |
| Released | 2023-11-02 | 2023-12-12 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
DeepSeek Coder 33B: 37.4 (#180), Phi-2: —
| Benchmark | DeepSeek Coder 33B | Phi-2 |
|---|---|---|
| HumanEval+ | 75% | 45.1% |
| MBPP+ | 70.1% | 54.2% |
| BigCodeBench Instruct | 42% | — |
| BigCodeBench Complete | 51.1% | — |
Reasoning Not comparable
DeepSeek Coder 33B: —, Phi-2: —
| Benchmark | DeepSeek Coder 33B | Phi-2 |
|---|---|---|
| Epoch Capabilities Index | 95.74 | 107.62 |
| WinoGrande | 62% | 54.7% |
| Adversarial NLI | — | 42.5% |
| BIG-Bench Hard | — | 59.4% |
| HellaSwag | — | 53.6% |
Math Not comparable
DeepSeek Coder 33B: —, Phi-2: —
| Benchmark | DeepSeek Coder 33B | Phi-2 |
|---|---|---|
| GSM8K | 35.4% | — |
Knowledge Not comparable
DeepSeek Coder 33B: —, Phi-2: —
| Benchmark | DeepSeek Coder 33B | Phi-2 |
|---|---|---|
| ARC (AI2) Challenge | 42.2% | 75.9% |
| MMLU | 39.4% | 58.4% |
| OpenBookQA | — | 73.6% |
| TriviaQA | — | 45.2% |
Frequently asked questions
Is DeepSeek Coder 33B better than Phi-2?
Neither DeepSeek Coder 33B nor Phi-2 has enough public benchmark results to be ranked yet; the rows below show what has been published.
How many benchmarks do DeepSeek Coder 33B and Phi-2 share?
6 benchmarks have published results for both models. DeepSeek Coder 33B has 9 scored results on Noometry and Phi-2 has 11.