# phi-3-medium 14B vs Yi 6B

> phi-3-medium 14B has enough public results to be ranked (#306); Yi 6B does not yet, so treat this comparison as directional.

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

## Summary

- They share 6 benchmarks with published results for both.

## Snapshot

| | phi-3-medium 14B | Yi 6B |
|---|---|---|
| Provider | Microsoft | 01.AI |
| Noometry Index | 29.1 | — |
| Rank | 306 | — |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- phi-3-medium 14B: 36.3 (#198)
- Yi 6B: —

| Benchmark | phi-3-medium 14B | Yi 6B |
|---|---|---|
| BigCodeBench Instruct | 37.6% | — |
| BigCodeBench Complete | 48.7% | — |

## Reasoning

- phi-3-medium 14B: —
- Yi 6B: —

| Benchmark | phi-3-medium 14B | Yi 6B |
|---|---|---|
| BIG-Bench Hard | 81.4% | 47.2% |
| Epoch Capabilities Index | 121.18 | 104.37 |
| HellaSwag | 82.4% | 74.4% |
| WinoGrande | 81.5% | 71.3% |
| Adversarial NLI | 55.8% | — |

## Math

- phi-3-medium 14B: 25.2 (#249)
- Yi 6B: —

| Benchmark | phi-3-medium 14B | Yi 6B |
|---|---|---|
| MATH Level 5 | 17.6% | — |
| GSM8K | — | 44.9% |

## Knowledge

- phi-3-medium 14B: 9.1 (#301)
- Yi 6B: —

| Benchmark | phi-3-medium 14B | Yi 6B |
|---|---|---|
| ARC (AI2) Challenge | 91.6% | 50.3% |
| MMLU | 78% | 64% |
| GPQA Diamond | 27.6% | — |
| OpenBookQA | 87.4% | — |
| TriviaQA | 73.9% | — |

## FAQ

### Is phi-3-medium 14B better than Yi 6B?

phi-3-medium 14B has enough public results to be ranked (#306); Yi 6B does not yet, so treat this comparison as directional.

### How many benchmarks do phi-3-medium 14B and Yi 6B share?

6 benchmarks have published results for both models. phi-3-medium 14B has 13 scored results on Noometry and Yi 6B has 7.