# Phi-4 vs Qwen3-1.7B

> Phi-4 is the stronger model overall, scoring 31.2 to 26.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/phi-4-vs-qwen3-1-7b
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Phi-4 scores higher in 2 categories and Qwen3-1.7B in 2 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Phi-4 leads 32.6 to 19.6.
- The biggest single-benchmark swing is GPQA Diamond: 56.1% for Phi-4 and 38% for Qwen3-1.7B.

## Snapshot

| | Phi-4 | Qwen3-1.7B |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 31.2 | 26.6 |
| Rank | 279 | 336 |
| Context | 128K | — |
| Input $/M | $0.07 | — |
| Output $/M | $0.14 | — |
| Weights | Open | Open |

## Coding

- Phi-4: 34.4 (#239)
- Qwen3-1.7B: —

| Benchmark | Phi-4 | Qwen3-1.7B |
|---|---|---|
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 30.7% | — |
| LMArena Coding | 1231 | — |
| BigCodeBench Complete | 55.4% | — |

## Agentic & Tool Use

- Phi-4: 22.8 (#128)
- Qwen3-1.7B: 24.7 (#115)

| Benchmark | Phi-4 | Qwen3-1.7B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 28.8% | 28.4% |
| BALROG | 11.6% | — |

## Reasoning

- Phi-4: 17.7 (#291)
- Qwen3-1.7B: 19.2 (#267)

| Benchmark | Phi-4 | Qwen3-1.7B |
|---|---|---|
| Chess Puzzles | 1% | 0% |
| LiveBench Reasoning | 47.8% | — |
| LMArena Hard Prompts | 1220 | — |
| LiveBench Data Analysis | 45.2% | — |
| Epoch Capabilities Index | 130.42 | — |
| LiveBench | 41.6% | — |

## Math

- Phi-4: 20.8 (#285)
- Qwen3-1.7B: 16.3 (#294)

| Benchmark | Phi-4 | Qwen3-1.7B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 13.8% | 8.1% |
| LiveBench Math | 42% | — |
| LMArena Math | 1246 | — |
| MATH Level 5 | 64.9% | — |

## Knowledge

- Phi-4: 32.6 (#209)
- Qwen3-1.7B: 19.6 (#278)

| Benchmark | Phi-4 | Qwen3-1.7B |
|---|---|---|
| GPQA Diamond | 56.1% | 38% |
| Confabulations | 29.4% | — |
| Vectara Hallucination Rate | 3.7% | — |
| LMArena Expert | 1203 | — |
| MMLU | 84.8% | — |

## Multilingual

- Phi-4: 37.2 (#237)
- Qwen3-1.7B: —

| Benchmark | Phi-4 | Qwen3-1.7B |
|---|---|---|
| LMArena Non-English | 1197 | — |
| LMArena Chinese | 1212 | — |
| LMArena French | 1224 | — |
| LMArena German | 1222 | — |
| LMArena Japanese | 1158 | — |
| LMArena Korean | 1151 | — |
| LMArena Russian | 1209 | — |
| LMArena Spanish | 1234 | — |

## Instruction Following

- Phi-4: 60.4 (#251)
- Qwen3-1.7B: —

| Benchmark | Phi-4 | Qwen3-1.7B |
|---|---|---|
| LiveBench Instruction Following | 58.4% | — |
| LMArena Instruction Following | 1201 | — |

## Long Context

- Phi-4: 36.9 (#226)
- Qwen3-1.7B: —

| Benchmark | Phi-4 | Qwen3-1.7B |
|---|---|---|
| LMArena Longer Query | 1217 | — |

## Writing & Preference

- Phi-4: 40.5 (#244)
- Qwen3-1.7B: —

| Benchmark | Phi-4 | Qwen3-1.7B |
|---|---|---|
| LMArena Text | 1217 | — |
| LMArena Creative Writing | 1182 | — |
| Short-Story Creative Writing | 62.6% | — |
| LMArena Multi-Turn | 1206 | — |
| LiveBench Language | 25.6% | — |

## FAQ

### Is Phi-4 better than Qwen3-1.7B?

Phi-4 is the stronger model overall, scoring 31.2 to 26.6 on the Noometry Index.

### How many benchmarks do Phi-4 and Qwen3-1.7B share?

4 benchmarks have published results for both models. Phi-4 has 37 scored results on Noometry and Qwen3-1.7B has 4.