# Phi-4 vs Qwen1.5-72B

> Phi-4 and Qwen1.5-72B score almost the same on the Noometry Index (31.2 vs 30.8), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/phi-4-vs-qwen1-5-72b
- Last updated: 2026-10-12
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. Phi-4 scores higher in 6 categories and Qwen1.5-72B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Phi-4 leads 32.6 to 11.5.
- The biggest single-benchmark swing is GPQA Diamond: 56.1% for Phi-4 and 28.8% for Qwen1.5-72B.

## Snapshot

| | Phi-4 | Qwen1.5-72B |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 31.2 | 30.8 |
| Rank | 279 | 285 |
| Context | 128K | — |
| Input $/M | $0.07 | — |
| Output $/M | $0.14 | — |
| Weights | Open | Open |

## Coding

- Phi-4: 34.4 (#239)
- Qwen1.5-72B: 31.9 (#277)

| Benchmark | Phi-4 | Qwen1.5-72B |
|---|---|---|
| BigCodeBench Instruct | 45.5% | 33.2% |
| LMArena Coding | 1231 | 1165 |
| BigCodeBench Complete | 55.4% | 40.3% |
| LiveBench Coding | 30.7% | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |

## Agentic & Tool Use

- Phi-4: 22.8 (#128)
- Qwen1.5-72B: —

| Benchmark | Phi-4 | Qwen1.5-72B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.8% | — |
| BALROG | 11.6% | — |

## Reasoning

- Phi-4: 17.7 (#291)
- Qwen1.5-72B: 22.2 (#203)

| Benchmark | Phi-4 | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1220 | 1148 |
| Chess Puzzles | 1% | — |
| LiveBench Reasoning | 47.8% | — |
| LiveBench Data Analysis | 45.2% | — |
| Epoch Capabilities Index | 130.42 | — |
| LiveBench | 41.6% | — |

## Math

- Phi-4: 20.8 (#285)
- Qwen1.5-72B: 33.2 (#205)

| Benchmark | Phi-4 | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1246 | 1164 |
| OTIS Mock AIME 2024-2025 | 13.8% | — |
| LiveBench Math | 42% | — |
| MATH Level 5 | 64.9% | — |

## Knowledge

- Phi-4: 32.6 (#209)
- Qwen1.5-72B: 11.5 (#300)

| Benchmark | Phi-4 | Qwen1.5-72B |
|---|---|---|
| GPQA Diamond | 56.1% | 28.8% |
| LMArena Expert | 1203 | 1136 |
| Confabulations | 29.4% | — |
| Vectara Hallucination Rate | 3.7% | — |
| MMLU | 84.8% | — |

## Multilingual

- Phi-4: 37.2 (#237)
- Qwen1.5-72B: 33.2 (#253)

| Benchmark | Phi-4 | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1197 | 1135 |
| LMArena Chinese | 1212 | 1186 |
| LMArena French | 1224 | 1159 |
| LMArena German | 1222 | 1084 |
| LMArena Japanese | 1158 | 1061 |
| LMArena Korean | 1151 | 1050 |
| LMArena Russian | 1209 | 1104 |
| LMArena Spanish | 1234 | 1110 |

## Instruction Following

- Phi-4: 60.4 (#251)
- Qwen1.5-72B: 59.3 (#256)

| Benchmark | Phi-4 | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1201 | 1141 |
| LiveBench Instruction Following | 58.4% | — |

## Long Context

- Phi-4: 36.9 (#226)
- Qwen1.5-72B: 35.1 (#243)

| Benchmark | Phi-4 | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1217 | 1157 |

## Writing & Preference

- Phi-4: 40.5 (#244)
- Qwen1.5-72B: 37.3 (#258)

| Benchmark | Phi-4 | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1217 | 1166 |
| LMArena Creative Writing | 1182 | 1137 |
| LMArena Multi-Turn | 1206 | 1160 |
| Short-Story Creative Writing | 62.6% | — |
| LiveBench Language | 25.6% | — |

## FAQ

### Is Phi-4 better than Qwen1.5-72B?

Phi-4 and Qwen1.5-72B score almost the same on the Noometry Index (31.2 vs 30.8), so choose on price, context window or the category you care about most.

### Is Phi-4 or Qwen1.5-72B better for coding?

Phi-4 scores higher on coding benchmarks: 34.4 versus 31.9 in the Noometry coding category.

### How many benchmarks do Phi-4 and Qwen1.5-72B share?

20 benchmarks have published results for both models. Phi-4 has 37 scored results on Noometry and Qwen1.5-72B has 22.