# Phi 3 Mini 4k Instruct June 2024 vs Qwen2-72B

> Phi 3 Mini 4k Instruct June 2024 is the stronger model overall, scoring 30.7 to 29.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/phi-3-mini-4k-instruct-june-vs-qwen2-72b
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Phi 3 Mini 4k Instruct June 2024 scores higher in 3 categories and Qwen2-72B in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2-72B leads 41.0 to 29.7.

## Snapshot

| | Phi 3 Mini 4k Instruct June 2024 | Qwen2-72B |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 30.7 | 29.5 |
| Rank | 274 | 294 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Phi 3 Mini 4k Instruct June 2024: 31.2 (#275)
- Qwen2-72B: 28.7 (#303)

| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1093 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |

## Agentic & Tool Use

- Phi 3 Mini 4k Instruct June 2024: —
- Qwen2-72B: 16.9 (#138)

| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |

## Reasoning

- Phi 3 Mini 4k Instruct June 2024: 19.9 (#229)
- Qwen2-72B: 22.2 (#184)

| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1088 | 1191 |
| Epoch Capabilities Index | — | 125.27 |

## Math

- Phi 3 Mini 4k Instruct June 2024: 30.4 (#209)
- Qwen2-72B: 27.9 (#232)

| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Qwen2-72B |
|---|---|---|
| LMArena Math | 1152 | 1235 |
| MATH Level 5 | — | 39.1% |

## Knowledge

- Phi 3 Mini 4k Instruct June 2024: 28.1 (#240)
- Qwen2-72B: 21.2 (#270)

| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1051 | 1171 |
| GPQA Diamond | — | 40.8% |
| MMLU | — | 82.4% |

## Multilingual

- Phi 3 Mini 4k Instruct June 2024: 26.0 (#277)
- Qwen2-72B: 36.0 (#239)

| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1013 | 1176 |
| LMArena Chinese | 1033 | 1240 |
| LMArena German | 1031 | 1151 |
| LMArena Japanese | 954 | 1111 |
| LMArena Korean | 880 | 1083 |
| LMArena Russian | 1019 | 1169 |
| LMArena French | — | 1169 |
| LMArena Spanish | — | 1168 |

## Instruction Following

- Phi 3 Mini 4k Instruct June 2024: 54.3 (#277)
- Qwen2-72B: 62.0 (#236)

| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1058 | 1181 |

## Long Context

- Phi 3 Mini 4k Instruct June 2024: 31.6 (#272)
- Qwen2-72B: 36.1 (#230)

| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1042 | 1193 |

## Writing & Preference

- Phi 3 Mini 4k Instruct June 2024: 29.7 (#289)
- Qwen2-72B: 41.0 (#236)

| Benchmark | Phi 3 Mini 4k Instruct June 2024 | Qwen2-72B |
|---|---|---|
| LMArena Text | 1080 | 1203 |
| LMArena Creative Writing | 1045 | 1181 |
| LMArena Multi-Turn | 1049 | 1195 |

## FAQ

### Is Phi 3 Mini 4k Instruct June 2024 better than Qwen2-72B?

Phi 3 Mini 4k Instruct June 2024 is the stronger model overall, scoring 30.7 to 29.5 on the Noometry Index.

### Is Phi 3 Mini 4k Instruct June 2024 or Qwen2-72B better for coding?

Phi 3 Mini 4k Instruct June 2024 scores higher on coding benchmarks: 31.2 versus 28.7 in the Noometry coding category.

### How many benchmarks do Phi 3 Mini 4k Instruct June 2024 and Qwen2-72B share?

15 benchmarks have published results for both models. Phi 3 Mini 4k Instruct June 2024 has 15 scored results on Noometry and Qwen2-72B has 26.