# phi-3-medium 14B vs Yi-34B

> phi-3-medium 14B is the stronger model overall, scoring 29.1 to 27.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/phi-3-medium-14b-vs-yi-34b
- Last updated: 2026-10-10
- Shared benchmarks: 5

## Summary

- They share 5 benchmarks with published results for both. phi-3-medium 14B scores higher in 3 categories and Yi-34B in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where phi-3-medium 14B leads 25.2 to 19.8.
- The biggest single-benchmark swing is GPQA Diamond: 27.6% for phi-3-medium 14B and 14.7% for Yi-34B.

## Snapshot

| | phi-3-medium 14B | Yi-34B |
|---|---|---|
| Provider | Microsoft | 01.AI |
| Noometry Index | 29.1 | 27.4 |
| Rank | 306 | 325 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- phi-3-medium 14B: 36.3 (#198)
- Yi-34B: 31.8 (#269)

| Benchmark | phi-3-medium 14B | Yi-34B |
|---|---|---|
| BigCodeBench Instruct | 37.6% | — |
| LMArena Coding | — | 1112 |
| BigCodeBench Complete | 48.7% | — |

## Reasoning

- phi-3-medium 14B: —
- Yi-34B: 20.3 (#222)

| Benchmark | phi-3-medium 14B | Yi-34B |
|---|---|---|
| BIG-Bench Hard | 81.4% | 71.7% |
| Epoch Capabilities Index | 121.18 | 117.28 |
| LMArena Hard Prompts | — | 1104 |
| Adversarial NLI | 55.8% | — |
| HellaSwag | 82.4% | — |
| WinoGrande | 81.5% | — |

## Math

- phi-3-medium 14B: 25.2 (#249)
- Yi-34B: 19.8 (#277)

| Benchmark | phi-3-medium 14B | Yi-34B |
|---|---|---|
| MATH Level 5 | 17.6% | 5.1% |
| LMArena Math | — | 1114 |
| GSM8K | — | 76% |

## Knowledge

- phi-3-medium 14B: 9.1 (#301)
- Yi-34B: 7.5 (#304)

| Benchmark | phi-3-medium 14B | Yi-34B |
|---|---|---|
| GPQA Diamond | 27.6% | 14.7% |
| MMLU | 78% | 76.3% |
| LMArena Expert | — | 1061 |
| ARC (AI2) Challenge | 91.6% | — |
| OpenBookQA | 87.4% | — |
| TriviaQA | 73.9% | — |

## Multilingual

- phi-3-medium 14B: —
- Yi-34B: 29.9 (#259)

| Benchmark | phi-3-medium 14B | Yi-34B |
|---|---|---|
| LMArena Non-English | — | 1079 |
| LMArena Chinese | — | 1175 |
| LMArena French | — | 1080 |
| LMArena German | — | 1042 |
| LMArena Japanese | — | 993 |
| LMArena Korean | — | 959 |
| LMArena Russian | — | 1050 |
| LMArena Spanish | — | 1070 |

## Instruction Following

- phi-3-medium 14B: —
- Yi-34B: 56.4 (#269)

| Benchmark | phi-3-medium 14B | Yi-34B |
|---|---|---|
| LMArena Instruction Following | — | 1091 |

## Long Context

- phi-3-medium 14B: —
- Yi-34B: 33.2 (#259)

| Benchmark | phi-3-medium 14B | Yi-34B |
|---|---|---|
| LMArena Longer Query | — | 1094 |

## Writing & Preference

- phi-3-medium 14B: —
- Yi-34B: 34.3 (#268)

| Benchmark | phi-3-medium 14B | Yi-34B |
|---|---|---|
| LMArena Text | — | 1129 |
| LMArena Creative Writing | — | 1108 |
| LMArena Multi-Turn | — | 1113 |

## FAQ

### Is phi-3-medium 14B better than Yi-34B?

phi-3-medium 14B is the stronger model overall, scoring 29.1 to 27.4 on the Noometry Index.

### Is phi-3-medium 14B or Yi-34B better for coding?

phi-3-medium 14B scores higher on coding benchmarks: 36.3 versus 31.8 in the Noometry coding category.

### How many benchmarks do phi-3-medium 14B and Yi-34B share?

5 benchmarks have published results for both models. phi-3-medium 14B has 13 scored results on Noometry and Yi-34B has 23.