# DeepSeek LLM 67B vs Qwen2-72B

> Qwen2-72B is the stronger model overall, scoring 30.0 to 24.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-qwen2-72b
- Last updated: 2026-10-12
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 1 category and Qwen2-72B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2-72B leads 30.2 to 8.7.
- The biggest single-benchmark swing is MATH Level 5: 6.4% for DeepSeek LLM 67B and 39.1% for Qwen2-72B.

## Snapshot

| | DeepSeek LLM 67B | Qwen2-72B |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 24.9 | 30.0 |
| Rank | 347 | 300 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- DeepSeek LLM 67B: 31.9 (#278)
- Qwen2-72B: 29.1 (#310)

| Benchmark | DeepSeek LLM 67B | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1096 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |

## Agentic & Tool Use

- DeepSeek LLM 67B: —
- Qwen2-72B: 17.0 (#146)

| Benchmark | DeepSeek LLM 67B | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |

## Reasoning

- DeepSeek LLM 67B: 16.5 (#304)
- Qwen2-72B: 23.2 (#181)

| Benchmark | DeepSeek LLM 67B | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1191 |
| Epoch Capabilities Index | 110.5 | 125.28 |
| Chess Puzzles | 0% | — |

## Math

- DeepSeek LLM 67B: 8.7 (#324)
- Qwen2-72B: 30.2 (#236)

| Benchmark | DeepSeek LLM 67B | Qwen2-72B |
|---|---|---|
| LMArena Math | 1108 | 1235 |
| MATH Level 5 | 6.4% | 39.1% |
| OTIS Mock AIME 2024-2025 | 0.8% | — |

## Knowledge

- DeepSeek LLM 67B: 7.0 (#313)
- Qwen2-72B: 21.2 (#275)

| Benchmark | DeepSeek LLM 67B | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 24.6% | 40.8% |
| LMArena Expert | — | 1171 |
| MMLU | — | 82.4% |

## Multilingual

- DeepSeek LLM 67B: 29.4 (#267)
- Qwen2-72B: 35.9 (#244)

| Benchmark | DeepSeek LLM 67B | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1073 | 1176 |
| LMArena Chinese | 1132 | 1240 |
| LMArena French | — | 1170 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Russian | — | 1169 |
| LMArena Spanish | — | 1169 |

## Instruction Following

- DeepSeek LLM 67B: 55.4 (#277)
- Qwen2-72B: 61.7 (#241)

| Benchmark | DeepSeek LLM 67B | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1079 | 1181 |

## Long Context

- DeepSeek LLM 67B: 33.1 (#265)
- Qwen2-72B: 36.1 (#235)

| Benchmark | DeepSeek LLM 67B | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1092 | 1192 |

## Writing & Preference

- DeepSeek LLM 67B: 31.6 (#282)
- Qwen2-72B: 40.8 (#241)

| Benchmark | DeepSeek LLM 67B | Qwen2-72B |
|---|---|---|
| LMArena Text | 1105 | 1203 |
| LMArena Creative Writing | 1067 | 1181 |
| LMArena Multi-Turn | 1082 | 1196 |

## FAQ

### Is DeepSeek LLM 67B better than Qwen2-72B?

Qwen2-72B is the stronger model overall, scoring 30.0 to 24.9 on the Noometry Index.

### Is DeepSeek LLM 67B or Qwen2-72B better for coding?

DeepSeek LLM 67B scores higher on coding benchmarks: 31.9 versus 29.1 in the Noometry coding category.

### How many benchmarks do DeepSeek LLM 67B and Qwen2-72B share?

13 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Qwen2-72B has 26.