# Phi-4 Mini vs Qwen3-Coder 480B-A35B Instruct

> Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 37.7 to 30.4 on the Noometry Index. Phi-4 Mini costs 23× less per token, which makes it the better buy when Qwen3-Coder 480B-A35B Instruct's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/phi-4-mini-vs-qwen3-coder-480b-a35b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in knowledge, where Qwen3-Coder 480B-A35B Instruct leads 36.4 to 24.8.
- Phi-4 Mini is cheaper at $0.075 / $0.30 per million input/output tokens, against $1.50 / $7.50 for Qwen3-Coder 480B-A35B Instruct.
- Qwen3-Coder 480B-A35B Instruct accepts more context: 262K tokens versus 128K.

## Snapshot

| | Phi-4 Mini | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 30.4 | 37.7 |
| Rank | 280 | 186 |
| Context | 128K | 262K |
| Input $/M | $0.075 | $1.50 |
| Output $/M | $0.30 | $7.50 |
| Weights | Open | Open |

## Coding

- Phi-4 Mini: 27.6 (#312)
- Qwen3-Coder 480B-A35B Instruct: 36.2 (#199)

| Benchmark | Phi-4 Mini | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| SWE-bench Verified (bash only) | — | 55.4% |
| LMArena WebDev | — | 1275 |
| SciCode | 10.8% | — |
| GSO | — | 4.9% |
| WeirdML | — | 41.2% |
| LMArena Coding | — | 1413 |
| ALE-Bench | — | 461.45 |
| AlgoTune | — | 1.44 |

## Agentic & Tool Use

- Phi-4 Mini: —
- Qwen3-Coder 480B-A35B Instruct: 23.7 (#116)

| Benchmark | Phi-4 Mini | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |

## Reasoning

- Phi-4 Mini: 21.7 (#190)
- Qwen3-Coder 480B-A35B Instruct: 24.7 (#141)

| Benchmark | Phi-4 Mini | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Kagi LLM Benchmark | — | 49.5% |
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 1372 |

## Math

- Phi-4 Mini: —
- Qwen3-Coder 480B-A35B Instruct: 34.9 (#151)

| Benchmark | Phi-4 Mini | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | — | 1364 |

## Knowledge

- Phi-4 Mini: 24.8 (#261)
- Qwen3-Coder 480B-A35B Instruct: 36.4 (#159)

| Benchmark | Phi-4 Mini | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Vectara Hallucination Rate | 23.5% | — |
| LMArena Expert | — | 1337 |

## Multilingual

- Phi-4 Mini: —
- Qwen3-Coder 480B-A35B Instruct: 47.8 (#143)

| Benchmark | Phi-4 Mini | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | — | 1345 |
| LMArena Chinese | — | 1356 |
| LMArena French | — | 1394 |
| LMArena German | — | 1324 |
| LMArena Japanese | — | 1309 |
| LMArena Korean | — | 1307 |
| LMArena Russian | — | 1367 |
| LMArena Spanish | — | 1360 |

## Instruction Following

- Phi-4 Mini: —
- Qwen3-Coder 480B-A35B Instruct: 71.8 (#142)

| Benchmark | Phi-4 Mini | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | — | 1356 |

## Long Context

- Phi-4 Mini: —
- Qwen3-Coder 480B-A35B Instruct: 42.0 (#126)

| Benchmark | Phi-4 Mini | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | — | 1379 |

## Writing & Preference

- Phi-4 Mini: —
- Qwen3-Coder 480B-A35B Instruct: 55.5 (#142)

| Benchmark | Phi-4 Mini | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | — | 1356 |
| LMArena Creative Writing | — | 1333 |
| LMArena Multi-Turn | — | 1365 |

## FAQ

### Is Phi-4 Mini better than Qwen3-Coder 480B-A35B Instruct?

Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 37.7 to 30.4 on the Noometry Index. Phi-4 Mini costs 23× less per token, which makes it the better buy when Qwen3-Coder 480B-A35B Instruct's lead doesn't matter for your workload.

### Which is cheaper, Phi-4 Mini or Qwen3-Coder 480B-A35B Instruct?

Phi-4 Mini is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; Qwen3-Coder 480B-A35B Instruct lists at $1.50 and $7.50.

### Is Phi-4 Mini or Qwen3-Coder 480B-A35B Instruct better for coding?

Qwen3-Coder 480B-A35B Instruct scores higher on coding benchmarks: 36.2 versus 27.6 in the Noometry coding category.

### Which has the bigger context window?

Qwen3-Coder 480B-A35B Instruct does, with 262K tokens against 128K.

### How many benchmarks do Phi-4 Mini and Qwen3-Coder 480B-A35B Instruct share?

0 benchmarks have published results for both models. Phi-4 Mini has 3 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.