# Phi-4 Mini vs Qwen3.5 35B-A3B

> Qwen3.5 35B-A3B is the stronger model overall, scoring 41.7 to 30.4 on the Noometry Index. Phi-4 Mini costs 5.2× less per token, which makes it the better buy when Qwen3.5 35B-A3B's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/phi-4-mini-vs-qwen3-5-35b-a3b
- Last updated: 2026-10-10
- Shared benchmarks: 3

## Summary

- They share 3 benchmarks with published results for both. Phi-4 Mini scores higher in 0 categories and Qwen3.5 35B-A3B in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5 35B-A3B leads 47.7 to 24.8.
- The biggest single-benchmark swing is SciCode: 10.8% for Phi-4 Mini and 29.3% for Qwen3.5 35B-A3B.
- Phi-4 Mini is cheaper at $0.075 / $0.30 per million input/output tokens, against $0.25 / $2 for Qwen3.5 35B-A3B.
- Qwen3.5 35B-A3B accepts more context: 262K tokens versus 128K.

## Snapshot

| | Phi-4 Mini | Qwen3.5 35B-A3B |
|---|---|---|
| Provider | Microsoft | Alibaba (Qwen) |
| Noometry Index | 30.4 | 41.7 |
| Rank | 280 | 118 |
| Context | 128K | 262K |
| Input $/M | $0.075 | $0.25 |
| Output $/M | $0.30 | $2 |
| Weights | Open | Open |

## Coding

- Phi-4 Mini: 27.6 (#312)
- Qwen3.5 35B-A3B: 33.5 (#244)

| Benchmark | Phi-4 Mini | Qwen3.5 35B-A3B |
|---|---|---|
| SciCode | 10.8% | 29.3% |
| LMArena WebDev | — | 1254 |
| LMArena Coding | — | 1410 |

## Reasoning

- Phi-4 Mini: 21.7 (#190)
- Qwen3.5 35B-A3B: 23.9 (#158)

| Benchmark | Phi-4 Mini | Qwen3.5 35B-A3B |
|---|---|---|
| CritPt | 0% | 0.6% |
| Chess Puzzles | — | 10% |
| LMArena Hard Prompts | — | 1400 |
| DTBench | — | 80% |
| LMCA | — | 29.5% |
| Epoch Capabilities Index | — | 142.52 |

## Math

- Phi-4 Mini: —
- Qwen3.5 35B-A3B: 38.4 (#86)

| Benchmark | Phi-4 Mini | Qwen3.5 35B-A3B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 56% |
| OTIS Mock AIME 2024-2025 | — | 70% |
| LMArena Math | — | 1404 |

## Knowledge

- Phi-4 Mini: 24.8 (#261)
- Qwen3.5 35B-A3B: 47.7 (#73)

| Benchmark | Phi-4 Mini | Qwen3.5 35B-A3B |
|---|---|---|
| Vectara Hallucination Rate | 23.5% | 10.5% |
| GPQA Diamond | — | 83.5% |
| LMArena Expert | — | 1408 |

## Multilingual

- Phi-4 Mini: —
- Qwen3.5 35B-A3B: 50.2 (#122)

| Benchmark | Phi-4 Mini | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Non-English | — | 1379 |
| LMArena Chinese | — | 1458 |
| LMArena French | — | 1412 |
| LMArena German | — | 1367 |
| LMArena Japanese | — | 1326 |
| LMArena Korean | — | 1354 |
| LMArena Russian | — | 1377 |
| LMArena Spanish | — | 1390 |

## Instruction Following

- Phi-4 Mini: —
- Qwen3.5 35B-A3B: 73.0 (#123)

| Benchmark | Phi-4 Mini | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Instruction Following | — | 1379 |

## Long Context

- Phi-4 Mini: —
- Qwen3.5 35B-A3B: 42.4 (#122)

| Benchmark | Phi-4 Mini | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Longer Query | — | 1390 |

## Writing & Preference

- Phi-4 Mini: —
- Qwen3.5 35B-A3B: 58.1 (#118)

| Benchmark | Phi-4 Mini | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Text | — | 1395 |
| LMArena Creative Writing | — | 1347 |
| LMArena Multi-Turn | — | 1391 |

## FAQ

### Is Phi-4 Mini better than Qwen3.5 35B-A3B?

Qwen3.5 35B-A3B is the stronger model overall, scoring 41.7 to 30.4 on the Noometry Index. Phi-4 Mini costs 5.2× less per token, which makes it the better buy when Qwen3.5 35B-A3B's lead doesn't matter for your workload.

### Which is cheaper, Phi-4 Mini or Qwen3.5 35B-A3B?

Phi-4 Mini is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; Qwen3.5 35B-A3B lists at $0.25 and $2.

### Is Phi-4 Mini or Qwen3.5 35B-A3B better for coding?

Qwen3.5 35B-A3B scores higher on coding benchmarks: 33.5 versus 27.6 in the Noometry coding category.

### Which has the bigger context window?

Qwen3.5 35B-A3B does, with 262K tokens against 128K.

### How many benchmarks do Phi-4 Mini and Qwen3.5 35B-A3B share?

3 benchmarks have published results for both models. Phi-4 Mini has 3 scored results on Noometry and Qwen3.5 35B-A3B has 28.