# DeepSeek-V2.5 (Sep 2024) vs Qwen3.6 Max Preview

> Qwen3.6 Max Preview is the stronger model overall, scoring 51.1 to 37.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v2-5-vs-qwen3-6-max-preview
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) 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 knowledge, where Qwen3.6 Max Preview leads 57.6 to 34.2.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 Max Preview |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 37.0 | 51.1 |
| Rank | 197 | 36 |
| Context | — | 262K |
| Input $/M | — | $1.30 |
| Output $/M | — | $7.80 |
| Weights | Open | Proprietary |

## Coding

- DeepSeek-V2.5 (Sep 2024): 31.3 (#274)
- Qwen3.6 Max Preview: 48.6 (#50)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Coding | 1310 | 1472 |
| SWE-bench Verified | — | 76.7% |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1482 |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |

## Agentic & Tool Use

- DeepSeek-V2.5 (Sep 2024): —
- Qwen3.6 Max Preview: —

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 Max Preview |
|---|---|---|
| Vending-Bench 2 | — | 4,254 |

## Reasoning

- DeepSeek-V2.5 (Sep 2024): 24.5 (#145)
- Qwen3.6 Max Preview: 40.8 (#47)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1457 |
| SimpleBench | — | 63% |
| NYT Connections (extended) | — | 74.1% |
| Chess Puzzles | — | 20% |
| Mystery Game Puzzles | — | 19% |
| DTBench | — | 87.2% |
| LMCA | — | 42.5% |
| Epoch Capabilities Index | — | 149.27 |

## Math

- DeepSeek-V2.5 (Sep 2024): 33.3 (#177)
- Qwen3.6 Max Preview: 52.2 (#40)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Math | 1289 | 1465 |
| OTIS Mock AIME 2024-2025 | — | 91.1% |
| FrontierMath (Feb 2025 set) | — | 23.1% |
| FrontierMath Tier 4 (v1) | — | 4.2% |

## Knowledge

- DeepSeek-V2.5 (Sep 2024): 34.2 (#190)
- Qwen3.6 Max Preview: 57.6 (#35)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Expert | 1266 | 1476 |
| GPQA Diamond | — | 87.4% |
| SimpleQA Verified | — | 52% |

## Multilingual

- DeepSeek-V2.5 (Sep 2024): 42.7 (#188)
- Qwen3.6 Max Preview: 54.3 (#46)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1273 | 1436 |
| LMArena Chinese | 1317 | 1487 |
| LMArena French | 1288 | 1449 |
| LMArena Russian | 1289 | 1444 |
| LMArena Spanish | 1248 | 1452 |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |

## Instruction Following

- DeepSeek-V2.5 (Sep 2024): 67.7 (#189)
- Qwen3.6 Max Preview: 75.8 (#51)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1280 | 1437 |

## Long Context

- DeepSeek-V2.5 (Sep 2024): 39.5 (#169)
- Qwen3.6 Max Preview: 44.6 (#59)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1301 | 1457 |

## Writing & Preference

- DeepSeek-V2.5 (Sep 2024): 50.0 (#182)
- Qwen3.6 Max Preview: 64.0 (#58)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1294 | 1447 |
| LMArena Creative Writing | 1285 | 1435 |
| LMArena Multi-Turn | 1297 | 1456 |

## FAQ

### Is DeepSeek-V2.5 (Sep 2024) better than Qwen3.6 Max Preview?

Qwen3.6 Max Preview is the stronger model overall, scoring 51.1 to 37.0 on the Noometry Index.

### Is DeepSeek-V2.5 (Sep 2024) or Qwen3.6 Max Preview better for coding?

Qwen3.6 Max Preview scores higher on coding benchmarks: 48.6 versus 31.3 in the Noometry coding category.

### How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Qwen3.6 Max Preview share?

14 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Qwen3.6 Max Preview has 29.