Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs Phi-2
Neither DeepSeek-V2 (MoE-236B, May 2024) nor Phi-2 has enough public benchmark results to be ranked yet; the rows below show what has been published.
Last verified . 7 shared benchmarks.
DeepSeek
MicrosoftSummary
- They share 7 benchmarks with published results for both.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | Phi-2 | |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 40.3 | — |
| Released | 2024-05-07 | 2023-12-12 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139), Phi-2: —
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Phi-2 |
|---|---|---|
| BigCodeBench Instruct | 48.9% | — |
| BigCodeBench Complete | 59.4% | — |
| HumanEval+ | — | 45.1% |
| MBPP+ | — | 54.2% |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Phi-2: —
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Phi-2 |
|---|---|---|
| BIG-Bench Hard | 78.8% | 59.4% |
| Epoch Capabilities Index | 124.77 | 107.94 |
| HellaSwag | 87.1% | 53.6% |
| WinoGrande | 86.3% | 54.7% |
| Adversarial NLI | — | 42.5% |
| PIQA | 83.9% | — |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Phi-2: —
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Phi-2 |
|---|---|---|
| ARC (AI2) Challenge | 92.2% | 75.9% |
| MMLU | 78.4% | 58.4% |
| TriviaQA | 80% | 45.2% |
| OpenBookQA | — | 73.6% |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than Phi-2?
Neither DeepSeek-V2 (MoE-236B, May 2024) 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-V2 (MoE-236B, May 2024) and Phi-2 share?
7 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Phi-2 has 11.