# DeepSeek-V2.5 (Sep 2024) vs Qwen1.5 4b Chat

> DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 28.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v2-5-vs-qwen1-5-4b-chat
- Last updated: 2026-10-12
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 8 categories and Qwen1.5 4b Chat in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V2.5 (Sep 2024) leads 49.8 to 23.8.

## Snapshot

| | DeepSeek-V2.5 (Sep 2024) | Qwen1.5 4b Chat |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 37.6 | 28.8 |
| Rank | 200 | 322 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- DeepSeek-V2.5 (Sep 2024): 31.7 (#281)
- Qwen1.5 4b Chat: 29.1 (#308)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Coding | 1309 | 999 |
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |

## Reasoning

- DeepSeek-V2.5 (Sep 2024): 25.6 (#145)
- Qwen1.5 4b Chat: 18.5 (#279)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Hard Prompts | 1289 | 976 |

## Math

- DeepSeek-V2.5 (Sep 2024): 35.9 (#177)
- Qwen1.5 4b Chat: 30.4 (#234)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Math | 1288 | 1026 |

## Knowledge

- DeepSeek-V2.5 (Sep 2024): 34.8 (#193)
- Qwen1.5 4b Chat: 26.7 (#255)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Expert | 1266 | 980 |

## Multilingual

- DeepSeek-V2.5 (Sep 2024): 42.5 (#193)
- Qwen1.5 4b Chat: 24.1 (#290)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Non-English | 1273 | 979 |
| LMArena Chinese | 1318 | 1024 |
| LMArena German | 1258 | 902 |
| LMArena Russian | 1289 | 952 |
| LMArena French | 1289 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Spanish | 1248 | — |

## Instruction Following

- DeepSeek-V2.5 (Sep 2024): 67.5 (#194)
- Qwen1.5 4b Chat: 49.0 (#300)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Instruction Following | 1280 | 978 |

## Long Context

- DeepSeek-V2.5 (Sep 2024): 39.5 (#174)
- Qwen1.5 4b Chat: 30.1 (#290)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Longer Query | 1301 | 988 |

## Writing & Preference

- DeepSeek-V2.5 (Sep 2024): 49.8 (#187)
- Qwen1.5 4b Chat: 23.8 (#309)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Text | 1294 | 997 |
| LMArena Creative Writing | 1285 | 969 |
| LMArena Multi-Turn | 1297 | 977 |

## FAQ

### Is DeepSeek-V2.5 (Sep 2024) better than Qwen1.5 4b Chat?

DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 28.8 on the Noometry Index.

### Is DeepSeek-V2.5 (Sep 2024) or Qwen1.5 4b Chat better for coding?

DeepSeek-V2.5 (Sep 2024) scores higher on coding benchmarks: 31.7 versus 29.1 in the Noometry coding category.

### How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Qwen1.5 4b Chat share?

13 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Qwen1.5 4b Chat has 13.