# DeepSeek Coder 6.7B vs Phi-2

> Neither DeepSeek Coder 6.7B 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-coder-6-7b-vs-phi-2
- Last updated: 2026-10-11
- Shared benchmarks: 6

## Summary

- They share 6 benchmarks with published results for both.

## Snapshot

| | DeepSeek Coder 6.7B | Phi-2 |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 37.6 | — |
| Rank | — | — |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- DeepSeek Coder 6.7B: 35.8 (#219)
- Phi-2: —

| Benchmark | DeepSeek Coder 6.7B | Phi-2 |
|---|---|---|
| HumanEval+ | 71.3% | 45.1% |
| MBPP+ | 65.6% | 54.2% |
| BigCodeBench Instruct | 35.5% | — |
| BigCodeBench Complete | 43.8% | — |

## Reasoning

- DeepSeek Coder 6.7B: —
- Phi-2: —

| Benchmark | DeepSeek Coder 6.7B | Phi-2 |
|---|---|---|
| Epoch Capabilities Index | 89.62 | 107.94 |
| WinoGrande | 57.6% | 54.7% |
| Adversarial NLI | — | 42.5% |
| BIG-Bench Hard | — | 59.4% |
| HellaSwag | — | 53.6% |

## Math

- DeepSeek Coder 6.7B: —
- Phi-2: —

| Benchmark | DeepSeek Coder 6.7B | Phi-2 |
|---|---|---|
| GSM8K | 21.3% | — |

## Knowledge

- DeepSeek Coder 6.7B: —
- Phi-2: —

| Benchmark | DeepSeek Coder 6.7B | Phi-2 |
|---|---|---|
| ARC (AI2) Challenge | 36.4% | 75.9% |
| MMLU | 36.4% | 58.4% |
| OpenBookQA | — | 73.6% |
| TriviaQA | — | 45.2% |

## FAQ

### Is DeepSeek Coder 6.7B better than Phi-2?

Neither DeepSeek Coder 6.7B 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 6.7B and Phi-2 share?

6 benchmarks have published results for both models. DeepSeek Coder 6.7B has 9 scored results on Noometry and Phi-2 has 11.