# Deepseek Coder v2 vs Qwen3.5 122B-A10B

> Qwen3.5 122B-A10B is the stronger model overall, scoring 41.6 to 35.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-coder-v2-vs-qwen3-5-122b-a10b
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 0 categories and Qwen3.5 122B-A10B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.5 122B-A10B leads 60.2 to 38.4.

## Snapshot

| | Deepseek Coder v2 | Qwen3.5 122B-A10B |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 35.3 | 41.6 |
| Rank | 217 | 120 |
| Context | — | 262K |
| Input $/M | — | $0.40 |
| Output $/M | — | $3.20 |
| Weights | Open | Open |

## Coding

- Deepseek Coder v2: 37.5 (#178)
- Qwen3.5 122B-A10B: 38.8 (#155)

| Benchmark | Deepseek Coder v2 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Coding | 1251 | 1436 |
| LMArena WebDev | — | 1360 |
| SciCode | — | 35.6% |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |

## Reasoning

- Deepseek Coder v2: 22.6 (#175)
- Qwen3.5 122B-A10B: 26.4 (#121)

| Benchmark | Deepseek Coder v2 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1421 |
| NYT Connections (extended) | — | 51.7% |
| CritPt | — | 0.9% |
| Thematic Generalization | — | 51.2% |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84.3% |
| LMCA | — | 32.2% |
| WinoGrande | 83.7% | — |

## Math

- Deepseek Coder v2: 32.3 (#188)
- Qwen3.5 122B-A10B: 36.4 (#114)

| Benchmark | Deepseek Coder v2 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Math | 1241 | 1432 |
| GSM8K | 94.5% | — |

## Knowledge

- Deepseek Coder v2: 31.7 (#209)
- Qwen3.5 122B-A10B: 38.2 (#138)

| Benchmark | Deepseek Coder v2 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Expert | 1181 | 1431 |
| Vectara Hallucination Rate | — | 11.2% |
| ARC (AI2) Challenge | 64.3% | — |

## Multimodal

- Deepseek Coder v2: —
- Qwen3.5 122B-A10B: 39.0 (#52)

| Benchmark | Deepseek Coder v2 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Vision | — | 1245 |

## Multilingual

- Deepseek Coder v2: 36.4 (#235)
- Qwen3.5 122B-A10B: 51.8 (#101)

| Benchmark | Deepseek Coder v2 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Non-English | 1182 | 1400 |
| LMArena Chinese | 1201 | 1462 |
| LMArena French | 1184 | 1442 |
| LMArena German | 1164 | 1425 |
| LMArena Japanese | 1126 | 1364 |
| LMArena Korean | 1104 | 1353 |
| LMArena Russian | 1188 | 1400 |
| LMArena Spanish | 1153 | 1423 |

## Instruction Following

- Deepseek Coder v2: 61.9 (#237)
- Qwen3.5 122B-A10B: 74.0 (#109)

| Benchmark | Deepseek Coder v2 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Instruction Following | 1180 | 1399 |

## Long Context

- Deepseek Coder v2: 37.0 (#219)
- Qwen3.5 122B-A10B: 43.0 (#105)

| Benchmark | Deepseek Coder v2 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Longer Query | 1219 | 1410 |

## Writing & Preference

- Deepseek Coder v2: 38.4 (#249)
- Qwen3.5 122B-A10B: 60.2 (#98)

| Benchmark | Deepseek Coder v2 | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Text | 1191 | 1417 |
| LMArena Creative Writing | 1120 | 1369 |
| LMArena Multi-Turn | 1176 | 1416 |

## FAQ

### Is Deepseek Coder v2 better than Qwen3.5 122B-A10B?

Qwen3.5 122B-A10B is the stronger model overall, scoring 41.6 to 35.3 on the Noometry Index.

### Is Deepseek Coder v2 or Qwen3.5 122B-A10B better for coding?

Qwen3.5 122B-A10B scores higher on coding benchmarks: 38.8 versus 37.5 in the Noometry coding category.

### How many benchmarks do Deepseek Coder v2 and Qwen3.5 122B-A10B share?

17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Qwen3.5 122B-A10B has 27.