# DeepSeek-V2.5 (Sep 2024) vs Qwen3 8B

> DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.0 to 33.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v2-5-vs-qwen3-8b
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where DeepSeek-V2.5 (Sep 2024) leads 24.5 to 16.1.

## Snapshot

| | DeepSeek-V2.5 (Sep 2024) | Qwen3 8B |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 37.0 | 33.3 |
| Rank | 197 | 237 |
| Context | — | 131K |
| Input $/M | — | $0.18 |
| Output $/M | — | $0.70 |
| Weights | Open | Open |

## Coding

- DeepSeek-V2.5 (Sep 2024): 31.3 (#274)
- Qwen3 8B: 33.4 (#245)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3 8B |
|---|---|---|
| Aider Polyglot | 17.8% | — |
| SciCode | — | 22.6% |
| BigCodeBench Instruct | 48.6% | — |
| LMArena Coding | 1310 | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |

## Agentic & Tool Use

- DeepSeek-V2.5 (Sep 2024): —
- Qwen3 8B: 29.9 (#71)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 42.6% |

## Reasoning

- DeepSeek-V2.5 (Sep 2024): 24.5 (#145)
- Qwen3 8B: 16.1 (#299)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3 8B |
|---|---|---|
| CritPt | — | 0% |
| Chess Puzzles | — | 5% |
| LMArena Hard Prompts | 1289 | — |
| DTBench | — | 59.7% |
| LMCA | — | 8.8% |
| Epoch Capabilities Index | — | 136.17 |

## Math

- DeepSeek-V2.5 (Sep 2024): 33.3 (#177)
- Qwen3 8B: 33.3 (#176)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 56.1% |
| LMArena Math | 1289 | — |

## Knowledge

- DeepSeek-V2.5 (Sep 2024): 34.2 (#190)
- Qwen3 8B: 36.1 (#164)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3 8B |
|---|---|---|
| GPQA Diamond | — | 56.8% |
| Vectara Hallucination Rate | — | 4.8% |
| LMArena Expert | 1266 | — |

## Multilingual

- DeepSeek-V2.5 (Sep 2024): 42.7 (#188)
- Qwen3 8B: —

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3 8B |
|---|---|---|
| LMArena Non-English | 1273 | — |
| LMArena Chinese | 1317 | — |
| LMArena French | 1288 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Russian | 1289 | — |
| LMArena Spanish | 1248 | — |

## Instruction Following

- DeepSeek-V2.5 (Sep 2024): 67.7 (#189)
- Qwen3 8B: —

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3 8B |
|---|---|---|
| LMArena Instruction Following | 1280 | — |

## Long Context

- DeepSeek-V2.5 (Sep 2024): 39.5 (#169)
- Qwen3 8B: 37.8 (#205)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3 8B |
|---|---|---|
| Fiction.LiveBench | — | 62.1% |
| LMArena Longer Query | 1301 | — |

## Writing & Preference

- DeepSeek-V2.5 (Sep 2024): 50.0 (#182)
- Qwen3 8B: —

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3 8B |
|---|---|---|
| LMArena Text | 1294 | — |
| LMArena Creative Writing | 1285 | — |
| LMArena Multi-Turn | 1297 | — |

## FAQ

### Is DeepSeek-V2.5 (Sep 2024) better than Qwen3 8B?

DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.0 to 33.3 on the Noometry Index.

### Is DeepSeek-V2.5 (Sep 2024) or Qwen3 8B better for coding?

Qwen3 8B scores higher on coding benchmarks: 33.4 versus 31.3 in the Noometry coding category.

### How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Qwen3 8B share?

0 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Qwen3 8B has 11.