# Deepseek Coder v2 vs Qwen3.6 Max Preview

> Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 35.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-coder-v2-vs-qwen3-6-max-preview
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. Deepseek Coder v2 scores higher in 0 categories and Qwen3.6 Max Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.6 Max Preview leads 63.8 to 38.2.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.

## Snapshot

| | Deepseek Coder v2 | Qwen3.6 Max Preview |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 35.9 | 51.5 |
| Rank | 220 | 43 |
| Context | — | 262K |
| Input $/M | — | $1.30 |
| Output $/M | — | $7.80 |
| Weights | Open | Proprietary |

## Coding

- Deepseek Coder v2: 38.1 (#183)
- Qwen3.6 Max Preview: 48.7 (#54)

| Benchmark | Deepseek Coder v2 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Coding | 1251 | 1471 |
| SWE-bench Verified | — | 76.7% |
| LMArena WebDev | — | 1482 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |

## Agentic & Tool Use

- Deepseek Coder v2: —
- Qwen3.6 Max Preview: —

| Benchmark | Deepseek Coder v2 | Qwen3.6 Max Preview |
|---|---|---|
| Vending-Bench 2 | — | 4,254 |

## Reasoning

- Deepseek Coder v2: 23.6 (#176)
- Qwen3.6 Max Preview: 41.7 (#53)

| Benchmark | Deepseek Coder v2 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1457 |
| SimpleBench | — | 63% |
| NYT Connections (extended) | — | 74.1% |
| Chess Puzzles | — | 20% |
| Mystery Game Puzzles | — | 19% |
| DTBench | — | 87.2% |
| LMCA | — | 42.5% |
| Epoch Capabilities Index | — | 149.24 |
| WinoGrande | 83.7% | — |

## Math

- Deepseek Coder v2: 34.9 (#190)
- Qwen3.6 Max Preview: 54.1 (#46)

| Benchmark | Deepseek Coder v2 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Math | 1241 | 1465 |
| OTIS Mock AIME 2024-2025 | — | 91.1% |
| FrontierMath (Feb 2025 set) | — | 23.1% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
| GSM8K | 94.5% | — |

## Knowledge

- Deepseek Coder v2: 32.3 (#212)
- Qwen3.6 Max Preview: 57.6 (#39)

| Benchmark | Deepseek Coder v2 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Expert | 1181 | 1478 |
| GPQA Diamond | — | 87.4% |
| SimpleQA Verified | — | 52% |
| ARC (AI2) Challenge | 64.3% | — |

## Multilingual

- Deepseek Coder v2: 36.3 (#240)
- Qwen3.6 Max Preview: 54.2 (#48)

| Benchmark | Deepseek Coder v2 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1182 | 1437 |
| LMArena Chinese | 1201 | 1487 |
| LMArena French | 1185 | 1449 |
| LMArena Russian | 1188 | 1445 |
| LMArena Spanish | 1153 | 1454 |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |

## Instruction Following

- Deepseek Coder v2: 61.7 (#242)
- Qwen3.6 Max Preview: 75.7 (#55)

| Benchmark | Deepseek Coder v2 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1180 | 1438 |

## Long Context

- Deepseek Coder v2: 37.0 (#224)
- Qwen3.6 Max Preview: 44.6 (#61)

| Benchmark | Deepseek Coder v2 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1219 | 1457 |

## Writing & Preference

- Deepseek Coder v2: 38.2 (#253)
- Qwen3.6 Max Preview: 63.8 (#60)

| Benchmark | Deepseek Coder v2 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1191 | 1447 |
| LMArena Creative Writing | 1120 | 1435 |
| LMArena Multi-Turn | 1177 | 1456 |

## FAQ

### Is Deepseek Coder v2 better than Qwen3.6 Max Preview?

Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 35.9 on the Noometry Index.

### Is Deepseek Coder v2 or Qwen3.6 Max Preview better for coding?

Qwen3.6 Max Preview scores higher on coding benchmarks: 48.7 versus 38.1 in the Noometry coding category.

### How many benchmarks do Deepseek Coder v2 and Qwen3.6 Max Preview share?

14 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Qwen3.6 Max Preview has 29.