# DeepSeek-V3.1 vs Qwen3.5 Max Preview

> Qwen3.5 Max Preview is the stronger model overall, scoring 45.3 to 42.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v3-1-vs-qwen3-5-max-preview
- Last updated: 2026-10-12
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 1 category and Qwen3.5 Max Preview in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where Qwen3.5 Max Preview leads 45.2 to 36.3.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-V3.1 | Qwen3.5 Max Preview |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 42.8 | 45.3 |
| Rank | 108 | 71 |
| Context | 164K | — |
| Input $/M | $0.25 | — |
| Output $/M | $0.95 | — |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V3.1: 40.3 (#144)
- Qwen3.5 Max Preview: 44.0 (#77)

| Benchmark | DeepSeek-V3.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Coding | 1417 | 1487 |
| WeirdML | 38.4% | — |

## Reasoning

- DeepSeek-V3.1: 27.9 (#110)
- Qwen3.5 Max Preview: 30.8 (#84)

| Benchmark | DeepSeek-V3.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1483 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |

## Math

- DeepSeek-V3.1: 38.9 (#122)
- Qwen3.5 Max Preview: 40.1 (#94)

| Benchmark | DeepSeek-V3.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Math | 1420 | 1474 |

## Knowledge

- DeepSeek-V3.1: 43.7 (#90)
- Qwen3.5 Max Preview: 41.8 (#107)

| Benchmark | DeepSeek-V3.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Expert | 1405 | 1489 |
| Vectara Hallucination Rate | 5.5% | — |

## Multilingual

- DeepSeek-V3.1: 51.6 (#106)
- Qwen3.5 Max Preview: 56.2 (#22)

| Benchmark | DeepSeek-V3.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Non-English | 1400 | 1465 |
| LMArena Chinese | 1469 | 1534 |
| LMArena French | 1447 | 1484 |
| LMArena German | 1411 | 1487 |
| LMArena Japanese | 1378 | 1495 |
| LMArena Korean | 1337 | 1438 |
| LMArena Russian | 1405 | 1471 |
| LMArena Spanish | 1431 | 1470 |

## Instruction Following

- DeepSeek-V3.1: 73.9 (#110)
- Qwen3.5 Max Preview: 77.0 (#31)

| Benchmark | DeepSeek-V3.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1400 | 1467 |

## Long Context

- DeepSeek-V3.1: 36.3 (#232)
- Qwen3.5 Max Preview: 45.2 (#45)

| Benchmark | DeepSeek-V3.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Longer Query | 1422 | 1476 |
| Fiction.LiveBench | 52.8% | — |

## Writing & Preference

- DeepSeek-V3.1: 60.3 (#98)
- Qwen3.5 Max Preview: 66.0 (#41)

| Benchmark | DeepSeek-V3.1 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Text | 1420 | 1470 |
| LMArena Creative Writing | 1401 | 1464 |
| LMArena Multi-Turn | 1408 | 1478 |
| EQ-Bench Creative Writing | 1436 | — |

## FAQ

### Is DeepSeek-V3.1 better than Qwen3.5 Max Preview?

Qwen3.5 Max Preview is the stronger model overall, scoring 45.3 to 42.8 on the Noometry Index.

### Is DeepSeek-V3.1 or Qwen3.5 Max Preview better for coding?

Qwen3.5 Max Preview scores higher on coding benchmarks: 44.0 versus 40.3 in the Noometry coding category.

### How many benchmarks do DeepSeek-V3.1 and Qwen3.5 Max Preview share?

17 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Qwen3.5 Max Preview has 17.