# 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.

- Canonical page: https://noometry.com/compare/deepseek-v2-vs-phi-2
- Last updated: 2026-10-11
- Shared benchmarks: 7

## Summary

- They share 7 benchmarks with published results for both.

## Snapshot

| | DeepSeek-V2 (MoE-236B, May 2024) | Phi-2 |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 40.3 | — |
| Rank | — | — |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- 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

- 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

- 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% |

## FAQ

### 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.