# Deepseek Coder v2 vs Qwen3.7 Max

> Qwen3.7 Max is the stronger model overall, scoring 51.4 to 35.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-coder-v2-vs-qwen3-7-max
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Deepseek Coder v2 scores higher in 0 categories and Qwen3.7 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.7 Max leads 62.3 to 32.3.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.

## Snapshot

| | Deepseek Coder v2 | Qwen3.7 Max |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 35.3 | 51.4 |
| Rank | 217 | 35 |
| Context | — | 1M |
| Input $/M | — | $2.50 |
| Output $/M | — | $7.50 |
| Weights | Open | Proprietary |

## Coding

- Deepseek Coder v2: 37.5 (#178)
- Qwen3.7 Max: 50.2 (#43)

| Benchmark | Deepseek Coder v2 | Qwen3.7 Max |
|---|---|---|
| LMArena Coding | 1251 | 1498 |
| SWE-bench Verified | — | 77.3% |
| LMArena WebDev | — | 1515 |
| SciCode | — | 48.8% |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| ALE-Bench | — | 1,189 |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |

## Agentic & Tool Use

- Deepseek Coder v2: —
- Qwen3.7 Max: 21.8 (#129)

| Benchmark | Deepseek Coder v2 | Qwen3.7 Max |
|---|---|---|
| GBAEval | — | 0.4% |

## Reasoning

- Deepseek Coder v2: 22.6 (#175)
- Qwen3.7 Max: 48.4 (#36)

| Benchmark | Deepseek Coder v2 | Qwen3.7 Max |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1483 |
| SimpleBench | — | 70.4% |
| NYT Connections (extended) | — | 85.1% |
| CritPt | — | 13.4% |
| Chess Puzzles | — | 19% |
| EBR-Bench | — | 9.5% |
| Mystery Game Puzzles | — | 32% |
| DTBench | — | 92.3% |
| LMCA | — | 44% |
| Epoch Capabilities Index | — | 153.74 |
| WinoGrande | 83.7% | — |

## Math

- Deepseek Coder v2: 32.3 (#188)
- Qwen3.7 Max: 62.3 (#26)

| Benchmark | Deepseek Coder v2 | Qwen3.7 Max |
|---|---|---|
| LMArena Math | 1241 | 1488 |
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 34.1% |
| OTIS Mock AIME 2024-2025 | — | 95.6% |
| ProofBench | — | 26% |
| GSM8K | 94.5% | — |

## Knowledge

- Deepseek Coder v2: 31.7 (#209)
- Qwen3.7 Max: 61.7 (#24)

| Benchmark | Deepseek Coder v2 | Qwen3.7 Max |
|---|---|---|
| LMArena Expert | 1181 | 1488 |
| GPQA Diamond | — | 90.9% |
| SimpleQA Verified | — | 55.8% |
| ARC (AI2) Challenge | 64.3% | — |

## Multilingual

- Deepseek Coder v2: 36.4 (#235)
- Qwen3.7 Max: 57.1 (#13)

| Benchmark | Deepseek Coder v2 | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1182 | 1475 |
| LMArena Chinese | 1201 | 1533 |
| LMArena Russian | 1188 | 1482 |
| LMArena French | 1184 | — |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Spanish | 1153 | — |

## Instruction Following

- Deepseek Coder v2: 61.9 (#237)
- Qwen3.7 Max: 76.9 (#34)

| Benchmark | Deepseek Coder v2 | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1180 | 1460 |

## Long Context

- Deepseek Coder v2: 37.0 (#219)
- Qwen3.7 Max: 45.4 (#34)

| Benchmark | Deepseek Coder v2 | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 1219 | 1484 |

## Writing & Preference

- Deepseek Coder v2: 38.4 (#249)
- Qwen3.7 Max: 65.2 (#52)

| Benchmark | Deepseek Coder v2 | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1191 | 1476 |
| LMArena Creative Writing | 1120 | 1450 |
| LMArena Multi-Turn | 1176 | 1482 |
| EQ-Bench 4 | — | 1110 |

## FAQ

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

Qwen3.7 Max is the stronger model overall, scoring 51.4 to 35.3 on the Noometry Index.

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

Qwen3.7 Max scores higher on coding benchmarks: 50.2 versus 37.5 in the Noometry coding category.

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

12 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Qwen3.7 Max has 33.