# DeepSeek Coder 6.7B vs phi-3-medium 14B

> phi-3-medium 14B has enough public results to be ranked (#306); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/deepseek-coder-6-7b-vs-phi-3-medium-14b
- Last updated: 2026-10-10
- Shared benchmarks: 6

## Summary

- They share 6 benchmarks with published results for both. DeepSeek Coder 6.7B scores higher in 0 categories and phi-3-medium 14B in 1 category; one gap is clear of the uncertainty.

## Snapshot

| | DeepSeek Coder 6.7B | phi-3-medium 14B |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 37.1 | 29.1 |
| Rank | — | 306 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- DeepSeek Coder 6.7B: 35.2 (#216)
- phi-3-medium 14B: 36.3 (#198)

| Benchmark | DeepSeek Coder 6.7B | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | 35.5% | 37.6% |
| BigCodeBench Complete | 43.8% | 48.7% |
| HumanEval+ | 71.3% | — |
| MBPP+ | 65.6% | — |

## Reasoning

- DeepSeek Coder 6.7B: —
- phi-3-medium 14B: —

| Benchmark | DeepSeek Coder 6.7B | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 88.88 | 121.18 |
| WinoGrande | 57.6% | 81.5% |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| HellaSwag | — | 82.4% |

## Math

- DeepSeek Coder 6.7B: —
- phi-3-medium 14B: 25.2 (#249)

| Benchmark | DeepSeek Coder 6.7B | phi-3-medium 14B |
|---|---|---|
| MATH Level 5 | — | 17.6% |
| GSM8K | 21.3% | — |

## Knowledge

- DeepSeek Coder 6.7B: —
- phi-3-medium 14B: 9.1 (#301)

| Benchmark | DeepSeek Coder 6.7B | phi-3-medium 14B |
|---|---|---|
| ARC (AI2) Challenge | 36.4% | 91.6% |
| MMLU | 36.4% | 78% |
| GPQA Diamond | — | 27.6% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |

## FAQ

### Is DeepSeek Coder 6.7B better than phi-3-medium 14B?

phi-3-medium 14B has enough public results to be ranked (#306); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.

### Is DeepSeek Coder 6.7B or phi-3-medium 14B better for coding?

phi-3-medium 14B scores higher on coding benchmarks: 36.3 versus 35.2 in the Noometry coding category.

### How many benchmarks do DeepSeek Coder 6.7B and phi-3-medium 14B share?

6 benchmarks have published results for both models. DeepSeek Coder 6.7B has 9 scored results on Noometry and phi-3-medium 14B has 13.