# DeepSeek-V3.1 vs Qwen1.5-72B

> DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 30.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v3-1-vs-qwen1-5-72b
- Last updated: 2026-10-12
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 8 categories and Qwen1.5-72B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3.1 leads 43.7 to 11.5.

## Snapshot

| | DeepSeek-V3.1 | Qwen1.5-72B |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 42.8 | 30.8 |
| Rank | 108 | 285 |
| Context | 164K | — |
| Input $/M | $0.25 | — |
| Output $/M | $0.95 | — |
| Weights | Open | Open |

## Coding

- DeepSeek-V3.1: 40.3 (#144)
- Qwen1.5-72B: 31.9 (#277)

| Benchmark | DeepSeek-V3.1 | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1417 | 1165 |
| WeirdML | 38.4% | — |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |

## Reasoning

- DeepSeek-V3.1: 27.9 (#110)
- Qwen1.5-72B: 22.2 (#203)

| Benchmark | DeepSeek-V3.1 | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1148 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |

## Math

- DeepSeek-V3.1: 38.9 (#122)
- Qwen1.5-72B: 33.2 (#205)

| Benchmark | DeepSeek-V3.1 | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1420 | 1164 |

## Knowledge

- DeepSeek-V3.1: 43.7 (#90)
- Qwen1.5-72B: 11.5 (#300)

| Benchmark | DeepSeek-V3.1 | Qwen1.5-72B |
|---|---|---|
| LMArena Expert | 1405 | 1136 |
| GPQA Diamond | — | 28.8% |
| Vectara Hallucination Rate | 5.5% | — |

## Multilingual

- DeepSeek-V3.1: 51.6 (#106)
- Qwen1.5-72B: 33.2 (#253)

| Benchmark | DeepSeek-V3.1 | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1400 | 1135 |
| LMArena Chinese | 1469 | 1186 |
| LMArena French | 1447 | 1159 |
| LMArena German | 1411 | 1084 |
| LMArena Japanese | 1378 | 1061 |
| LMArena Korean | 1337 | 1050 |
| LMArena Russian | 1405 | 1104 |
| LMArena Spanish | 1431 | 1110 |

## Instruction Following

- DeepSeek-V3.1: 73.9 (#110)
- Qwen1.5-72B: 59.3 (#256)

| Benchmark | DeepSeek-V3.1 | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1400 | 1141 |

## Long Context

- DeepSeek-V3.1: 36.3 (#232)
- Qwen1.5-72B: 35.1 (#243)

| Benchmark | DeepSeek-V3.1 | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1422 | 1157 |
| Fiction.LiveBench | 52.8% | — |

## Writing & Preference

- DeepSeek-V3.1: 60.3 (#98)
- Qwen1.5-72B: 37.3 (#258)

| Benchmark | DeepSeek-V3.1 | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1420 | 1166 |
| LMArena Creative Writing | 1401 | 1137 |
| LMArena Multi-Turn | 1408 | 1160 |
| EQ-Bench Creative Writing | 1436 | — |

## FAQ

### Is DeepSeek-V3.1 better than Qwen1.5-72B?

DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 30.8 on the Noometry Index.

### Is DeepSeek-V3.1 or Qwen1.5-72B better for coding?

DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 31.9 in the Noometry coding category.

### How many benchmarks do DeepSeek-V3.1 and Qwen1.5-72B share?

17 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Qwen1.5-72B has 22.