# DeepSeek-V3.2-Speciale vs Yi-34B

> DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.1 to 27.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v3-2-speciale-vs-yi-34b
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where DeepSeek-V3.2-Speciale leads 32.1 to 20.3.

## Snapshot

| | DeepSeek-V3.2-Speciale | Yi-34B |
|---|---|---|
| Provider | DeepSeek | 01.AI |
| Noometry Index | 39.1 | 27.4 |
| Rank | 159 | 325 |
| Context | 128K | — |
| Input $/M | $0.58 | — |
| Output $/M | $1.68 | — |
| Weights | Open | Open |

## Coding

- DeepSeek-V3.2-Speciale: 39.9 (#136)
- Yi-34B: 31.8 (#269)

| Benchmark | DeepSeek-V3.2-Speciale | Yi-34B |
|---|---|---|
| WeirdML | 46.7% | — |
| LMArena Coding | — | 1112 |

## Reasoning

- DeepSeek-V3.2-Speciale: 32.1 (#65)
- Yi-34B: 20.3 (#222)

| Benchmark | DeepSeek-V3.2-Speciale | Yi-34B |
|---|---|---|
| SimpleBench | 52.6% | — |
| LMArena Hard Prompts | — | 1104 |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | — | 117.28 |

## Math

- DeepSeek-V3.2-Speciale: —
- Yi-34B: 19.8 (#277)

| Benchmark | DeepSeek-V3.2-Speciale | Yi-34B |
|---|---|---|
| LMArena Math | — | 1114 |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |

## Knowledge

- DeepSeek-V3.2-Speciale: —
- Yi-34B: 7.5 (#304)

| Benchmark | DeepSeek-V3.2-Speciale | Yi-34B |
|---|---|---|
| GPQA Diamond | — | 14.7% |
| LMArena Expert | — | 1061 |
| MMLU | — | 76.3% |

## Multilingual

- DeepSeek-V3.2-Speciale: —
- Yi-34B: 29.9 (#259)

| Benchmark | DeepSeek-V3.2-Speciale | Yi-34B |
|---|---|---|
| LMArena Non-English | — | 1079 |
| LMArena Chinese | — | 1175 |
| LMArena French | — | 1080 |
| LMArena German | — | 1042 |
| LMArena Japanese | — | 993 |
| LMArena Korean | — | 959 |
| LMArena Russian | — | 1050 |
| LMArena Spanish | — | 1070 |

## Instruction Following

- DeepSeek-V3.2-Speciale: —
- Yi-34B: 56.4 (#269)

| Benchmark | DeepSeek-V3.2-Speciale | Yi-34B |
|---|---|---|
| LMArena Instruction Following | — | 1091 |

## Long Context

- DeepSeek-V3.2-Speciale: —
- Yi-34B: 33.2 (#259)

| Benchmark | DeepSeek-V3.2-Speciale | Yi-34B |
|---|---|---|
| LMArena Longer Query | — | 1094 |

## Writing & Preference

- DeepSeek-V3.2-Speciale: 46.1 (#217)
- Yi-34B: 34.3 (#268)

| Benchmark | DeepSeek-V3.2-Speciale | Yi-34B |
|---|---|---|
| LMArena Text | — | 1129 |
| LMArena Creative Writing | — | 1108 |
| EQ-Bench Creative Writing | 1276 | — |
| LMArena Multi-Turn | — | 1113 |

## FAQ

### Is DeepSeek-V3.2-Speciale better than Yi-34B?

DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.1 to 27.4 on the Noometry Index.

### Is DeepSeek-V3.2-Speciale or Yi-34B better for coding?

DeepSeek-V3.2-Speciale scores higher on coding benchmarks: 39.9 versus 31.8 in the Noometry coding category.

### How many benchmarks do DeepSeek-V3.2-Speciale and Yi-34B share?

0 benchmarks have published results for both models. DeepSeek-V3.2-Speciale has 3 scored results on Noometry and Yi-34B has 23.