# DeepSeek-V3.2-Speciale vs Yi-Lightning

> DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.1 to 36.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v3-2-speciale-vs-yi-lightning
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where DeepSeek-V3.2-Speciale leads 39.9 to 27.0.
- DeepSeek-V3.2-Speciale has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-V3.2-Speciale | Yi-Lightning |
|---|---|---|
| Provider | DeepSeek | 01.AI |
| Noometry Index | 39.1 | 36.5 |
| Rank | 159 | 206 |
| Context | 128K | — |
| Input $/M | $0.58 | — |
| Output $/M | $1.68 | — |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V3.2-Speciale: 39.9 (#136)
- Yi-Lightning: 27.0 (#315)

| Benchmark | DeepSeek-V3.2-Speciale | Yi-Lightning |
|---|---|---|
| Aider Polyglot | — | 12.9% |
| WeirdML | 46.7% | — |
| LMArena Coding | — | 1313 |

## Reasoning

- DeepSeek-V3.2-Speciale: 32.1 (#65)
- Yi-Lightning: 24.9 (#137)

| Benchmark | DeepSeek-V3.2-Speciale | Yi-Lightning |
|---|---|---|
| SimpleBench | 52.6% | — |
| LMArena Hard Prompts | — | 1302 |

## Math

- DeepSeek-V3.2-Speciale: —
- Yi-Lightning: 33.5 (#173)

| Benchmark | DeepSeek-V3.2-Speciale | Yi-Lightning |
|---|---|---|
| LMArena Math | — | 1300 |

## Knowledge

- DeepSeek-V3.2-Speciale: —
- Yi-Lightning: 34.8 (#182)

| Benchmark | DeepSeek-V3.2-Speciale | Yi-Lightning |
|---|---|---|
| LMArena Expert | — | 1286 |

## Multilingual

- DeepSeek-V3.2-Speciale: —
- Yi-Lightning: 42.4 (#191)

| Benchmark | DeepSeek-V3.2-Speciale | Yi-Lightning |
|---|---|---|
| LMArena Non-English | — | 1269 |
| LMArena Chinese | — | 1320 |
| LMArena French | — | 1304 |
| LMArena German | — | 1267 |
| LMArena Japanese | — | 1228 |
| LMArena Korean | — | 1192 |
| LMArena Russian | — | 1255 |
| LMArena Spanish | — | 1315 |

## Instruction Following

- DeepSeek-V3.2-Speciale: —
- Yi-Lightning: 67.6 (#191)

| Benchmark | DeepSeek-V3.2-Speciale | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | — | 1278 |

## Long Context

- DeepSeek-V3.2-Speciale: —
- Yi-Lightning: 39.4 (#176)

| Benchmark | DeepSeek-V3.2-Speciale | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | — | 1297 |

## Writing & Preference

- DeepSeek-V3.2-Speciale: 46.1 (#217)
- Yi-Lightning: 50.4 (#178)

| Benchmark | DeepSeek-V3.2-Speciale | Yi-Lightning |
|---|---|---|
| LMArena Text | — | 1302 |
| LMArena Creative Writing | — | 1280 |
| EQ-Bench Creative Writing | 1276 | — |
| LMArena Multi-Turn | — | 1311 |

## FAQ

### Is DeepSeek-V3.2-Speciale better than Yi-Lightning?

DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.1 to 36.5 on the Noometry Index.

### Is DeepSeek-V3.2-Speciale or Yi-Lightning better for coding?

DeepSeek-V3.2-Speciale scores higher on coding benchmarks: 39.9 versus 27.0 in the Noometry coding category.

### How many benchmarks do DeepSeek-V3.2-Speciale and Yi-Lightning share?

0 benchmarks have published results for both models. DeepSeek-V3.2-Speciale has 3 scored results on Noometry and Yi-Lightning has 18.