# DeepSeek-V3.2-Speciale vs Phi-3.5-mini

> DeepSeek-V3.2-Speciale has enough public results to be ranked (#159); Phi-3.5-mini does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/deepseek-v3-2-speciale-vs-phi-3-5-mini
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where DeepSeek-V3.2-Speciale leads 39.9 to 34.0.

## Snapshot

| | DeepSeek-V3.2-Speciale | Phi-3.5-mini |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 39.1 | 36.4 |
| Rank | 159 | — |
| Context | 128K | — |
| Input $/M | $0.58 | — |
| Output $/M | $1.68 | — |
| Weights | Open | Open |

## Coding

- DeepSeek-V3.2-Speciale: 39.9 (#136)
- Phi-3.5-mini: 34.0 (#231)

| Benchmark | DeepSeek-V3.2-Speciale | Phi-3.5-mini |
|---|---|---|
| WeirdML | 46.7% | — |
| BigCodeBench Instruct | — | 32.8% |
| BigCodeBench Complete | — | 38.5% |

## Reasoning

- DeepSeek-V3.2-Speciale: 32.1 (#65)
- Phi-3.5-mini: —

| Benchmark | DeepSeek-V3.2-Speciale | Phi-3.5-mini |
|---|---|---|
| SimpleBench | 52.6% | — |
| PIQA | — | 81% |

## Math

- DeepSeek-V3.2-Speciale: —
- Phi-3.5-mini: —

| Benchmark | DeepSeek-V3.2-Speciale | Phi-3.5-mini |
|---|---|---|
| GSM8K | — | 86.2% |

## Knowledge

- DeepSeek-V3.2-Speciale: —
- Phi-3.5-mini: —

| Benchmark | DeepSeek-V3.2-Speciale | Phi-3.5-mini |
|---|---|---|
| BoolQ | — | 78% |

## Writing & Preference

- DeepSeek-V3.2-Speciale: 46.1 (#217)
- Phi-3.5-mini: —

| Benchmark | DeepSeek-V3.2-Speciale | Phi-3.5-mini |
|---|---|---|
| EQ-Bench Creative Writing | 1276 | — |

## FAQ

### Is DeepSeek-V3.2-Speciale better than Phi-3.5-mini?

DeepSeek-V3.2-Speciale has enough public results to be ranked (#159); Phi-3.5-mini does not yet, so treat this comparison as directional.

### Is DeepSeek-V3.2-Speciale or Phi-3.5-mini better for coding?

DeepSeek-V3.2-Speciale scores higher on coding benchmarks: 39.9 versus 34.0 in the Noometry coding category.

### How many benchmarks do DeepSeek-V3.2-Speciale and Phi-3.5-mini share?

0 benchmarks have published results for both models. DeepSeek-V3.2-Speciale has 3 scored results on Noometry and Phi-3.5-mini has 5.