# DeepSeek Coder 1.3B vs Qwen2-72B

> Qwen2-72B has enough public results to be ranked (#300); DeepSeek Coder 1.3B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/deepseek-coder-1-3b-vs-qwen2-72b
- Last updated: 2026-10-11
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. DeepSeek Coder 1.3B scores higher in 1 category and Qwen2-72B in 0 categories; one gap is clear of the uncertainty.
- The biggest single-benchmark swing is BigCodeBench Complete: 29.6% for DeepSeek Coder 1.3B and 54% for Qwen2-72B.

## Snapshot

| | DeepSeek Coder 1.3B | Qwen2-72B |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 35.0 | 30.0 |
| Rank | — | 300 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- DeepSeek Coder 1.3B: 31.2 (#287)
- Qwen2-72B: 29.1 (#310)

| Benchmark | DeepSeek Coder 1.3B | Qwen2-72B |
|---|---|---|
| BigCodeBench Instruct | 22.8% | 38.5% |
| BigCodeBench Complete | 29.6% | 54% |
| WeirdML | — | 11.3% |
| LMArena Coding | — | 1196 |
| HumanEval+ | 60.4% | — |
| MBPP+ | 54.8% | — |

## Agentic & Tool Use

- DeepSeek Coder 1.3B: —
- Qwen2-72B: 17.0 (#146)

| Benchmark | DeepSeek Coder 1.3B | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |

## Reasoning

- DeepSeek Coder 1.3B: —
- Qwen2-72B: 23.2 (#181)

| Benchmark | DeepSeek Coder 1.3B | Qwen2-72B |
|---|---|---|
| Epoch Capabilities Index | 63.6 | 125.28 |
| LMArena Hard Prompts | — | 1191 |
| WinoGrande | 53.3% | — |

## Math

- DeepSeek Coder 1.3B: —
- Qwen2-72B: 30.2 (#236)

| Benchmark | DeepSeek Coder 1.3B | Qwen2-72B |
|---|---|---|
| LMArena Math | — | 1235 |
| MATH Level 5 | — | 39.1% |
| GSM8K | 4.4% | — |

## Knowledge

- DeepSeek Coder 1.3B: —
- Qwen2-72B: 21.2 (#275)

| Benchmark | DeepSeek Coder 1.3B | Qwen2-72B |
|---|---|---|
| MMLU | 25.8% | 82.4% |
| GPQA Diamond | — | 40.8% |
| LMArena Expert | — | 1171 |
| ARC (AI2) Challenge | 25.4% | — |

## Multilingual

- DeepSeek Coder 1.3B: —
- Qwen2-72B: 35.9 (#244)

| Benchmark | DeepSeek Coder 1.3B | Qwen2-72B |
|---|---|---|
| LMArena Non-English | — | 1176 |
| LMArena Chinese | — | 1240 |
| LMArena French | — | 1170 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Russian | — | 1169 |
| LMArena Spanish | — | 1169 |

## Instruction Following

- DeepSeek Coder 1.3B: —
- Qwen2-72B: 61.7 (#241)

| Benchmark | DeepSeek Coder 1.3B | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | — | 1181 |

## Long Context

- DeepSeek Coder 1.3B: —
- Qwen2-72B: 36.1 (#235)

| Benchmark | DeepSeek Coder 1.3B | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | — | 1192 |

## Writing & Preference

- DeepSeek Coder 1.3B: —
- Qwen2-72B: 40.8 (#241)

| Benchmark | DeepSeek Coder 1.3B | Qwen2-72B |
|---|---|---|
| LMArena Text | — | 1203 |
| LMArena Creative Writing | — | 1181 |
| LMArena Multi-Turn | — | 1196 |

## FAQ

### Is DeepSeek Coder 1.3B better than Qwen2-72B?

Qwen2-72B has enough public results to be ranked (#300); DeepSeek Coder 1.3B does not yet, so treat this comparison as directional.

### Is DeepSeek Coder 1.3B or Qwen2-72B better for coding?

DeepSeek Coder 1.3B scores higher on coding benchmarks: 31.2 versus 29.1 in the Noometry coding category.

### How many benchmarks do DeepSeek Coder 1.3B and Qwen2-72B share?

4 benchmarks have published results for both models. DeepSeek Coder 1.3B has 9 scored results on Noometry and Qwen2-72B has 26.