# Phi 3 Medium 4k Instruct vs Qwen2-72B

> Phi 3 Medium 4k Instruct is the stronger model overall, scoring 32.4 to 29.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/phi-3-medium-4k-instruct-vs-qwen2-72b
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Phi 3 Medium 4k Instruct scores higher in 3 categories and Qwen2-72B in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Phi 3 Medium 4k Instruct leads 29.6 to 21.2.

## Snapshot

| | Phi 3 Medium 4k Instruct | Qwen2-72B |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 32.4 | 29.5 |
| Rank | 246 | 294 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Phi 3 Medium 4k Instruct: 32.3 (#263)
- Qwen2-72B: 28.7 (#303)

| Benchmark | Phi 3 Medium 4k Instruct | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1130 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |

## Agentic & Tool Use

- Phi 3 Medium 4k Instruct: —
- Qwen2-72B: 16.9 (#138)

| Benchmark | Phi 3 Medium 4k Instruct | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |

## Reasoning

- Phi 3 Medium 4k Instruct: 20.8 (#214)
- Qwen2-72B: 22.2 (#184)

| Benchmark | Phi 3 Medium 4k Instruct | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1127 | 1191 |
| Epoch Capabilities Index | — | 125.27 |

## Math

- Phi 3 Medium 4k Instruct: 30.9 (#202)
- Qwen2-72B: 27.9 (#232)

| Benchmark | Phi 3 Medium 4k Instruct | Qwen2-72B |
|---|---|---|
| LMArena Math | 1173 | 1235 |
| MATH Level 5 | — | 39.1% |

## Knowledge

- Phi 3 Medium 4k Instruct: 29.6 (#226)
- Qwen2-72B: 21.2 (#270)

| Benchmark | Phi 3 Medium 4k Instruct | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1108 | 1171 |
| GPQA Diamond | — | 40.8% |
| MMLU | — | 82.4% |

## Multilingual

- Phi 3 Medium 4k Instruct: 30.8 (#258)
- Qwen2-72B: 36.0 (#239)

| Benchmark | Phi 3 Medium 4k Instruct | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1094 | 1176 |
| LMArena Chinese | 1108 | 1240 |
| LMArena French | 1109 | 1169 |
| LMArena German | 1101 | 1151 |
| LMArena Japanese | 1042 | 1111 |
| LMArena Korean | 954 | 1083 |
| LMArena Russian | 1145 | 1169 |
| LMArena Spanish | 1095 | 1168 |

## Instruction Following

- Phi 3 Medium 4k Instruct: 57.8 (#263)
- Qwen2-72B: 62.0 (#236)

| Benchmark | Phi 3 Medium 4k Instruct | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1114 | 1181 |

## Long Context

- Phi 3 Medium 4k Instruct: 33.9 (#250)
- Qwen2-72B: 36.1 (#230)

| Benchmark | Phi 3 Medium 4k Instruct | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1120 | 1193 |

## Writing & Preference

- Phi 3 Medium 4k Instruct: 34.3 (#267)
- Qwen2-72B: 41.0 (#236)

| Benchmark | Phi 3 Medium 4k Instruct | Qwen2-72B |
|---|---|---|
| LMArena Text | 1138 | 1203 |
| LMArena Creative Writing | 1106 | 1181 |
| LMArena Multi-Turn | 1088 | 1195 |

## FAQ

### Is Phi 3 Medium 4k Instruct better than Qwen2-72B?

Phi 3 Medium 4k Instruct is the stronger model overall, scoring 32.4 to 29.5 on the Noometry Index.

### Is Phi 3 Medium 4k Instruct or Qwen2-72B better for coding?

Phi 3 Medium 4k Instruct scores higher on coding benchmarks: 32.3 versus 28.7 in the Noometry coding category.

### How many benchmarks do Phi 3 Medium 4k Instruct and Qwen2-72B share?

17 benchmarks have published results for both models. Phi 3 Medium 4k Instruct has 17 scored results on Noometry and Qwen2-72B has 26.