# DeepSeek-R1 vs Qwen2.5-Coder-32B

> DeepSeek-R1 is the stronger model overall, scoring 42.0 to 32.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-r1-vs-qwen2-5-coder-32b
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. DeepSeek-R1 scores higher in 7 categories and Qwen2.5-Coder-32B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-R1 leads 45.9 to 22.4.
- The biggest single-benchmark swing is Aider Polyglot: 71.4% for DeepSeek-R1 and 16.4% for Qwen2.5-Coder-32B.
- Qwen2.5-Coder-32B is cheaper at $0.66 / $1 per million input/output tokens, against $0.50 / $2.15 for DeepSeek-R1.
- DeepSeek-R1 accepts more context: 164K tokens versus 33K.
- Qwen2.5-Coder-32B has downloadable open weights; the other is API-only.

## Snapshot

| | DeepSeek-R1 | Qwen2.5-Coder-32B |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 42.0 | 32.9 |
| Rank | 110 | 239 |
| Context | 164K | 33K |
| Input $/M | $0.50 | $0.66 |
| Output $/M | $2.15 | $1 |
| Weights | Proprietary | Open |

## Coding

- DeepSeek-R1: 45.9 (#63)
- Qwen2.5-Coder-32B: 22.4 (#328)

| Benchmark | DeepSeek-R1 | Qwen2.5-Coder-32B |
|---|---|---|
| Aider Polyglot | 71.4% | 16.4% |
| LiveBench Coding | 66.7% | 56.9% |
| LMArena Coding | 1427 | 1276 |
| SWE-bench Verified (bash only) | — | 9% |
| SciCode | 35.7% | — |
| WeirdML | 41.6% | — |
| BigCodeBench Instruct | — | 49% |
| BigCodeBench Complete | — | 58% |
| ALE-Bench | 804.12 | — |
| AlgoTune | 1.7 | — |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |

## Agentic & Tool Use

- DeepSeek-R1: 30.4 (#68)
- Qwen2.5-Coder-32B: —

| Benchmark | DeepSeek-R1 | Qwen2.5-Coder-32B |
|---|---|---|
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| METR Time Horizons | 53.8% | — |

## Reasoning

- DeepSeek-R1: 18.7 (#253)
- Qwen2.5-Coder-32B: 20.4 (#220)

| Benchmark | DeepSeek-R1 | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Reasoning | 83.2% | 42.1% |
| LMArena Hard Prompts | 1415 | 1251 |
| LiveBench Data Analysis | 69.8% | 49.9% |
| Epoch Capabilities Index | 141.3 | 119.41 |
| LiveBench | 71.6% | 46.2% |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 40.8% | — |
| Kagi LLM Benchmark | 69.4% | — |
| ARC-AGI-1 | 21.2% | — |
| CritPt | 1.1% | — |
| ForecastBench | 60 | — |
| HellaSwag | — | 83% |
| WinoGrande | — | 80.8% |

## Math

- DeepSeek-R1: 42.0 (#70)
- Qwen2.5-Coder-32B: 30.8 (#203)

| Benchmark | DeepSeek-R1 | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Math | 80.7% | 46.6% |
| LMArena Math | 1401 | 1251 |
| OTIS Mock AIME 2024-2025 | 66.4% | — |
| Omni-MATH | 42.4% | — |
| MATH Level 5 | 96.6% | — |
| GSM8K | — | 93% |

## Knowledge

- DeepSeek-R1: 44.3 (#81)
- Qwen2.5-Coder-32B: 32.9 (#200)

| Benchmark | DeepSeek-R1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1394 | 1221 |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.3% | — |
| Confabulations | 12.7% | — |
| Vectara Hallucination Rate | 11.3% | — |
| GPQA (HELM) | 66.6% | — |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |

## Multilingual

- DeepSeek-R1: 52.6 (#80)
- Qwen2.5-Coder-32B: 38.0 (#230)

| Benchmark | DeepSeek-R1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1412 | 1205 |
| LMArena Chinese | 1443 | 1222 |
| LMArena Russian | 1423 | 1228 |
| LMArena French | 1415 | — |
| LMArena German | 1405 | — |
| LMArena Japanese | 1394 | — |
| LMArena Korean | 1359 | — |
| LMArena Spanish | 1410 | — |

## Instruction Following

- DeepSeek-R1: 72.2 (#138)
- Qwen2.5-Coder-32B: 61.6 (#240)

| Benchmark | DeepSeek-R1 | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Instruction Following | 80.5% | 58.7% |
| LMArena Instruction Following | 1382 | 1223 |
| IFEval | 78.4% | — |

## Long Context

- DeepSeek-R1: 45.4 (#36)
- Qwen2.5-Coder-32B: 37.9 (#204)

| Benchmark | DeepSeek-R1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1391 | 1251 |
| Fiction.LiveBench | 75% | — |

## Writing & Preference

- DeepSeek-R1: 61.5 (#84)
- Qwen2.5-Coder-32B: 41.8 (#235)

| Benchmark | DeepSeek-R1 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1428 | 1230 |
| LMArena Creative Writing | 1406 | 1174 |
| LMArena Multi-Turn | 1404 | 1222 |
| LiveBench Language | 48.5% | 23.3% |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1500 | — |
| WildBench | 82.8% | — |

## FAQ

### Is DeepSeek-R1 better than Qwen2.5-Coder-32B?

DeepSeek-R1 is the stronger model overall, scoring 42.0 to 32.9 on the Noometry Index.

### Which is cheaper, DeepSeek-R1 or Qwen2.5-Coder-32B?

Qwen2.5-Coder-32B is cheaper. It lists at $0.66 per million input tokens and $1 per million output tokens; DeepSeek-R1 lists at $0.50 and $2.15.

### Is DeepSeek-R1 or Qwen2.5-Coder-32B better for coding?

DeepSeek-R1 scores higher on coding benchmarks: 45.9 versus 22.4 in the Noometry coding category.

### Which has the bigger context window?

DeepSeek-R1 does, with 164K tokens against 33K.

### How many benchmarks do DeepSeek-R1 and Qwen2.5-Coder-32B share?

21 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Qwen2.5-Coder-32B has 31.