# Deepseek Coder v2 vs Qwen3.7 Plus

> Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 35.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-coder-v2-vs-qwen3-7-plus
- 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 Qwen3.7 Plus in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.7 Plus leads 64.5 to 38.4.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.

## Snapshot

| | Deepseek Coder v2 | Qwen3.7 Plus |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 35.3 | 45.0 |
| Rank | 217 | 66 |
| Context | — | 1M |
| Input $/M | — | $0.40 |
| Output $/M | — | $1.60 |
| Weights | Open | Proprietary |

## Coding

- Deepseek Coder v2: 37.5 (#178)
- Qwen3.7 Plus: 36.1 (#200)

| Benchmark | Deepseek Coder v2 | Qwen3.7 Plus |
|---|---|---|
| LMArena Coding | 1251 | 1473 |
| FrontierCode | — | 10.2% |
| SciCode | — | 45.5% |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |

## Agentic & Tool Use

- Deepseek Coder v2: —
- Qwen3.7 Plus: 21.2 (#130)

| Benchmark | Deepseek Coder v2 | Qwen3.7 Plus |
|---|---|---|
| OSWorld 2.0 | — | 2.8% |

## Reasoning

- Deepseek Coder v2: 22.6 (#175)
- Qwen3.7 Plus: 38.4 (#54)

| Benchmark | Deepseek Coder v2 | Qwen3.7 Plus |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1460 |
| NYT Connections (extended) | — | 74.8% |
| CritPt | — | 9.1% |
| Chess Puzzles | — | 24% |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84% |
| LMCA | — | 37.6% |
| Epoch Capabilities Index | — | 147.39 |
| WinoGrande | 83.7% | — |

## Math

- Deepseek Coder v2: 32.3 (#188)
- Qwen3.7 Plus: 49.3 (#47)

| Benchmark | Deepseek Coder v2 | Qwen3.7 Plus |
|---|---|---|
| LMArena Math | 1241 | 1467 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| GSM8K | 94.5% | — |

## Knowledge

- Deepseek Coder v2: 31.7 (#209)
- Qwen3.7 Plus: 54.9 (#46)

| Benchmark | Deepseek Coder v2 | Qwen3.7 Plus |
|---|---|---|
| LMArena Expert | 1181 | 1467 |
| GPQA Diamond | — | 87.9% |
| ARC (AI2) Challenge | 64.3% | — |

## Multimodal

- Deepseek Coder v2: —
- Qwen3.7 Plus: 41.2 (#30)

| Benchmark | Deepseek Coder v2 | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1281 |
| LMArena Document | — | 1444 |

## Multilingual

- Deepseek Coder v2: 36.4 (#235)
- Qwen3.7 Plus: 55.0 (#36)

| Benchmark | Deepseek Coder v2 | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1182 | 1445 |
| LMArena Chinese | 1201 | 1510 |
| LMArena French | 1184 | 1471 |
| LMArena German | 1164 | 1471 |
| LMArena Japanese | 1126 | 1411 |
| LMArena Korean | 1104 | 1416 |
| LMArena Russian | 1188 | 1457 |
| LMArena Spanish | 1153 | 1453 |

## Instruction Following

- Deepseek Coder v2: 61.9 (#237)
- Qwen3.7 Plus: 75.9 (#49)

| Benchmark | Deepseek Coder v2 | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1180 | 1439 |

## Long Context

- Deepseek Coder v2: 37.0 (#219)
- Qwen3.7 Plus: 44.5 (#61)

| Benchmark | Deepseek Coder v2 | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1219 | 1454 |

## Writing & Preference

- Deepseek Coder v2: 38.4 (#249)
- Qwen3.7 Plus: 64.5 (#54)

| Benchmark | Deepseek Coder v2 | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1191 | 1454 |
| LMArena Creative Writing | 1120 | 1439 |
| LMArena Multi-Turn | 1176 | 1459 |

## FAQ

### Is Deepseek Coder v2 better than Qwen3.7 Plus?

Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 35.3 on the Noometry Index.

### Is Deepseek Coder v2 or Qwen3.7 Plus better for coding?

Deepseek Coder v2 scores higher on coding benchmarks: 37.5 versus 36.1 in the Noometry coding category.

### How many benchmarks do Deepseek Coder v2 and Qwen3.7 Plus share?

17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Qwen3.7 Plus has 32.