# Deepseek Coder v2 vs Qwen3.5 35B-A3B

> Qwen3.5 35B-A3B is the stronger model overall, scoring 41.7 to 35.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-coder-v2-vs-qwen3-5-35b-a3b
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 1 category and Qwen3.5 35B-A3B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.5 35B-A3B leads 58.1 to 38.4.

## Snapshot

| | Deepseek Coder v2 | Qwen3.5 35B-A3B |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 35.3 | 41.7 |
| Rank | 217 | 118 |
| Context | — | 262K |
| Input $/M | — | $0.25 |
| Output $/M | — | $2 |
| Weights | Open | Open |

## Coding

- Deepseek Coder v2: 37.5 (#178)
- Qwen3.5 35B-A3B: 33.5 (#244)

| Benchmark | Deepseek Coder v2 | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Coding | 1251 | 1410 |
| LMArena WebDev | — | 1254 |
| SciCode | — | 29.3% |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |

## Reasoning

- Deepseek Coder v2: 22.6 (#175)
- Qwen3.5 35B-A3B: 23.9 (#158)

| Benchmark | Deepseek Coder v2 | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1400 |
| CritPt | — | 0.6% |
| Chess Puzzles | — | 10% |
| DTBench | — | 80% |
| LMCA | — | 29.5% |
| Epoch Capabilities Index | — | 142.52 |
| WinoGrande | 83.7% | — |

## Math

- Deepseek Coder v2: 32.3 (#188)
- Qwen3.5 35B-A3B: 38.4 (#86)

| Benchmark | Deepseek Coder v2 | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Math | 1241 | 1404 |
| MathArena Final-Answer Competitions | — | 56% |
| OTIS Mock AIME 2024-2025 | — | 70% |
| GSM8K | 94.5% | — |

## Knowledge

- Deepseek Coder v2: 31.7 (#209)
- Qwen3.5 35B-A3B: 47.7 (#73)

| Benchmark | Deepseek Coder v2 | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Expert | 1181 | 1408 |
| GPQA Diamond | — | 83.5% |
| Vectara Hallucination Rate | — | 10.5% |
| ARC (AI2) Challenge | 64.3% | — |

## Multilingual

- Deepseek Coder v2: 36.4 (#235)
- Qwen3.5 35B-A3B: 50.2 (#122)

| Benchmark | Deepseek Coder v2 | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Non-English | 1182 | 1379 |
| LMArena Chinese | 1201 | 1458 |
| LMArena French | 1184 | 1412 |
| LMArena German | 1164 | 1367 |
| LMArena Japanese | 1126 | 1326 |
| LMArena Korean | 1104 | 1354 |
| LMArena Russian | 1188 | 1377 |
| LMArena Spanish | 1153 | 1390 |

## Instruction Following

- Deepseek Coder v2: 61.9 (#237)
- Qwen3.5 35B-A3B: 73.0 (#123)

| Benchmark | Deepseek Coder v2 | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Instruction Following | 1180 | 1379 |

## Long Context

- Deepseek Coder v2: 37.0 (#219)
- Qwen3.5 35B-A3B: 42.4 (#122)

| Benchmark | Deepseek Coder v2 | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Longer Query | 1219 | 1390 |

## Writing & Preference

- Deepseek Coder v2: 38.4 (#249)
- Qwen3.5 35B-A3B: 58.1 (#118)

| Benchmark | Deepseek Coder v2 | Qwen3.5 35B-A3B |
|---|---|---|
| LMArena Text | 1191 | 1395 |
| LMArena Creative Writing | 1120 | 1347 |
| LMArena Multi-Turn | 1176 | 1391 |

## FAQ

### Is Deepseek Coder v2 better than Qwen3.5 35B-A3B?

Qwen3.5 35B-A3B is the stronger model overall, scoring 41.7 to 35.3 on the Noometry Index.

### Is Deepseek Coder v2 or Qwen3.5 35B-A3B better for coding?

Deepseek Coder v2 scores higher on coding benchmarks: 37.5 versus 33.5 in the Noometry coding category.

### How many benchmarks do Deepseek Coder v2 and Qwen3.5 35B-A3B share?

17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Qwen3.5 35B-A3B has 28.