# DeepSeek-V2.5 (Sep 2024) vs Qwen3.6 27B

> Qwen3.6 27B is the stronger model overall, scoring 42.2 to 37.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v2-5-vs-qwen3-6-27b
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in knowledge, where Qwen3.6 27B leads 52.4 to 34.8.

## Snapshot

| | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 27B |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 37.6 | 42.2 |
| Rank | 200 | 117 |
| Context | — | 262K |
| Input $/M | — | $0.60 |
| Output $/M | — | $3.60 |
| Weights | Open | Open |

## Coding

- DeepSeek-V2.5 (Sep 2024): 31.7 (#281)
- Qwen3.6 27B: 39.1 (#163)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 27B |
|---|---|---|
| Aider Polyglot | 17.8% | — |
| SciCode | — | 37.3% |
| BigCodeBench Instruct | 48.6% | — |
| LMArena Coding | 1309 | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |

## Reasoning

- DeepSeek-V2.5 (Sep 2024): 25.6 (#145)
- Qwen3.6 27B: 25.0 (#153)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 27B |
|---|---|---|
| CritPt | — | 0.9% |
| Chess Puzzles | — | 22% |
| LMArena Hard Prompts | 1289 | — |
| Mystery Game Puzzles | — | 7% |
| DTBench | — | 78.1% |
| LMCA | — | 34.5% |
| Epoch Capabilities Index | — | 146.5 |

## Math

- DeepSeek-V2.5 (Sep 2024): 35.9 (#177)
- Qwen3.6 27B: 48.5 (#62)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 27B |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 35.1% |
| OTIS Mock AIME 2024-2025 | — | 91.1% |
| LMArena Math | 1288 | — |

## Knowledge

- DeepSeek-V2.5 (Sep 2024): 34.8 (#193)
- Qwen3.6 27B: 52.4 (#63)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 27B |
|---|---|---|
| GPQA Diamond | — | 85.9% |
| LMArena Expert | 1266 | — |

## Multilingual

- DeepSeek-V2.5 (Sep 2024): 42.5 (#193)
- Qwen3.6 27B: —

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 27B |
|---|---|---|
| LMArena Non-English | 1273 | — |
| LMArena Chinese | 1318 | — |
| LMArena French | 1289 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Russian | 1289 | — |
| LMArena Spanish | 1248 | — |

## Instruction Following

- DeepSeek-V2.5 (Sep 2024): 67.5 (#194)
- Qwen3.6 27B: —

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 27B |
|---|---|---|
| LMArena Instruction Following | 1280 | — |

## Long Context

- DeepSeek-V2.5 (Sep 2024): 39.5 (#174)
- Qwen3.6 27B: —

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 27B |
|---|---|---|
| LMArena Longer Query | 1301 | — |

## Writing & Preference

- DeepSeek-V2.5 (Sep 2024): 49.8 (#187)
- Qwen3.6 27B: 50.3 (#181)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 27B |
|---|---|---|
| LMArena Text | 1294 | — |
| LMArena Creative Writing | 1285 | — |
| EQ-Bench 4 | — | 1026 |
| LMArena Multi-Turn | 1297 | — |

## FAQ

### Is DeepSeek-V2.5 (Sep 2024) better than Qwen3.6 27B?

Qwen3.6 27B is the stronger model overall, scoring 42.2 to 37.6 on the Noometry Index.

### Is DeepSeek-V2.5 (Sep 2024) or Qwen3.6 27B better for coding?

Qwen3.6 27B scores higher on coding benchmarks: 39.1 versus 31.7 in the Noometry coding category.

### How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Qwen3.6 27B share?

0 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Qwen3.6 27B has 11.