# DeepSeek-V3.1 vs Qwen2-72B

> DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 29.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v3-1-vs-qwen2-72b
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 8 categories and Qwen2-72B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3.1 leads 43.0 to 21.2.
- The biggest single-benchmark swing is WeirdML: 38.4% for DeepSeek-V3.1 and 11.3% for Qwen2-72B.

## Snapshot

| | DeepSeek-V3.1 | Qwen2-72B |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 42.2 | 29.5 |
| Rank | 106 | 294 |
| Context | 164K | — |
| Input $/M | $0.25 | — |
| Output $/M | $0.95 | — |
| Weights | Open | Open |

## Coding

- DeepSeek-V3.1: 39.8 (#140)
- Qwen2-72B: 28.7 (#303)

| Benchmark | DeepSeek-V3.1 | Qwen2-72B |
|---|---|---|
| WeirdML | 38.4% | 11.3% |
| LMArena Coding | 1417 | 1196 |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |

## Agentic & Tool Use

- DeepSeek-V3.1: —
- Qwen2-72B: 16.9 (#138)

| Benchmark | DeepSeek-V3.1 | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |

## Reasoning

- DeepSeek-V3.1: 27.3 (#109)
- Qwen2-72B: 22.2 (#184)

| Benchmark | DeepSeek-V3.1 | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1191 |
| Epoch Capabilities Index | 139.92 | 125.27 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| ForecastBench | 58 | — |

## Math

- DeepSeek-V3.1: 36.1 (#125)
- Qwen2-72B: 27.9 (#232)

| Benchmark | DeepSeek-V3.1 | Qwen2-72B |
|---|---|---|
| LMArena Math | 1420 | 1235 |
| MATH Level 5 | — | 39.1% |

## Knowledge

- DeepSeek-V3.1: 43.0 (#86)
- Qwen2-72B: 21.2 (#270)

| Benchmark | DeepSeek-V3.1 | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1403 | 1171 |
| GPQA Diamond | — | 40.8% |
| Vectara Hallucination Rate | 5.5% | — |
| MMLU | — | 82.4% |

## Multilingual

- DeepSeek-V3.1: 51.8 (#100)
- Qwen2-72B: 36.0 (#239)

| Benchmark | DeepSeek-V3.1 | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1400 | 1176 |
| LMArena Chinese | 1470 | 1240 |
| LMArena French | 1447 | 1169 |
| LMArena German | 1412 | 1151 |
| LMArena Japanese | 1374 | 1111 |
| LMArena Korean | 1337 | 1083 |
| LMArena Russian | 1405 | 1169 |
| LMArena Spanish | 1429 | 1168 |

## Instruction Following

- DeepSeek-V3.1: 74.1 (#105)
- Qwen2-72B: 62.0 (#236)

| Benchmark | DeepSeek-V3.1 | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1400 | 1181 |

## Long Context

- DeepSeek-V3.1: 36.3 (#227)
- Qwen2-72B: 36.1 (#230)

| Benchmark | DeepSeek-V3.1 | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1422 | 1193 |
| Fiction.LiveBench | 52.8% | — |

## Writing & Preference

- DeepSeek-V3.1: 60.5 (#93)
- Qwen2-72B: 41.0 (#236)

| Benchmark | DeepSeek-V3.1 | Qwen2-72B |
|---|---|---|
| LMArena Text | 1420 | 1203 |
| LMArena Creative Writing | 1401 | 1181 |
| LMArena Multi-Turn | 1408 | 1195 |
| EQ-Bench Creative Writing | 1436 | — |

## FAQ

### Is DeepSeek-V3.1 better than Qwen2-72B?

DeepSeek-V3.1 is the stronger model overall, scoring 42.2 to 29.5 on the Noometry Index.

### Is DeepSeek-V3.1 or Qwen2-72B better for coding?

DeepSeek-V3.1 scores higher on coding benchmarks: 39.8 versus 28.7 in the Noometry coding category.

### How many benchmarks do DeepSeek-V3.1 and Qwen2-72B share?

19 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Qwen2-72B has 26.