# Claude Sonnet 5 vs Qwen2.5-Coder-32B

> Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 33.4 on the Noometry Index. Qwen2.5-Coder-32B costs 5.4× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/claude-sonnet-5-vs-qwen2-5-coder-32b
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Claude Sonnet 5 scores higher in 8 categories and Qwen2.5-Coder-32B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 5 leads 66.2 to 33.3.
- Qwen2.5-Coder-32B is cheaper at $0.66 / $1 per million input/output tokens, against $2 / $10 for Claude Sonnet 5.
- Claude Sonnet 5 accepts more context: 1M tokens versus 33K.
- Qwen2.5-Coder-32B has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Sonnet 5 | Qwen2.5-Coder-32B |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 54.6 | 33.4 |
| Rank | 29 | 245 |
| Context | 1M | 33K |
| Input $/M | $2 | $0.66 |
| Output $/M | $10 | $1 |
| Weights | Proprietary | Open |

## Coding

- Claude Sonnet 5: 55.5 (#26)
- Qwen2.5-Coder-32B: 22.6 (#333)

| Benchmark | Claude Sonnet 5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Coding | 1483 | 1276 |
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| CursorBench | 34.1% | — |
| LMArena WebDev | 1541 | — |
| SciCode | 54.3% | — |
| GSO | 37.3% | — |
| WeirdML | 68.8% | — |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
| ALE-Bench | 1,463 | — |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |

## Agentic & Tool Use

- Claude Sonnet 5: 42.8 (#18)
- Qwen2.5-Coder-32B: —

| Benchmark | Claude Sonnet 5 | Qwen2.5-Coder-32B |
|---|---|---|
| APEX-Agents | 54.5% | — |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |
| Vending-Bench 2 | 6,378 | — |

## Reasoning

- Claude Sonnet 5: 49.1 (#39)
- Qwen2.5-Coder-32B: 21.2 (#225)

| Benchmark | Claude Sonnet 5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1461 | 1251 |
| Epoch Capabilities Index | 156.21 | 119.49 |
| SimpleBench | 60.6% | — |
| NYT Connections (extended) | 75.1% | — |
| CritPt | 16.9% | — |
| Chess Puzzles | 35% | — |
| LiveBench Reasoning | — | 42.1% |
| Mystery Game Puzzles | 35% | — |
| DTBench | 92.5% | — |
| LiveBench Data Analysis | — | 49.9% |
| LMCA | 50% | — |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
| ForecastBench | 61.1 | — |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |

## Math

- Claude Sonnet 5: 66.2 (#27)
- Qwen2.5-Coder-32B: 33.3 (#204)

| Benchmark | Claude Sonnet 5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1467 | 1251 |
| FrontierMath (Tiers 1-3) | 65.6% | — |
| FrontierMath Tier 4 | 29.3% | — |
| OTIS Mock AIME 2024-2025 | 94.7% | — |
| ProofBench | 77% | — |
| LiveBench Math | — | 46.6% |
| GSM8K | — | 93% |

## Knowledge

- Claude Sonnet 5: 55.6 (#47)
- Qwen2.5-Coder-32B: 33.4 (#203)

| Benchmark | Claude Sonnet 5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1490 | 1221 |
| GPQA Diamond | 90.5% | — |
| SimpleQA Verified | 33.7% | — |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |

## Multimodal

- Claude Sonnet 5: 42.4 (#31)
- Qwen2.5-Coder-32B: —

| Benchmark | Claude Sonnet 5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Vision | 1274 | — |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |

## Multilingual

- Claude Sonnet 5: 53.8 (#55)
- Qwen2.5-Coder-32B: 37.8 (#235)

| Benchmark | Claude Sonnet 5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1431 | 1205 |
| LMArena Chinese | 1477 | 1222 |
| LMArena Russian | 1451 | 1228 |
| LMArena French | 1460 | — |
| LMArena German | 1440 | — |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1411 | — |
| LMArena Spanish | 1437 | — |

## Instruction Following

- Claude Sonnet 5: 76.3 (#41)
- Qwen2.5-Coder-32B: 61.4 (#245)

| Benchmark | Claude Sonnet 5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1452 | 1223 |
| LiveBench Instruction Following | — | 58.7% |

## Long Context

- Claude Sonnet 5: 44.8 (#55)
- Qwen2.5-Coder-32B: 38.0 (#208)

| Benchmark | Claude Sonnet 5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1463 | 1251 |

## Writing & Preference

- Claude Sonnet 5: 69.2 (#25)
- Qwen2.5-Coder-32B: 41.6 (#240)

| Benchmark | Claude Sonnet 5 | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1442 | 1230 |
| LMArena Creative Writing | 1416 | 1174 |
| LMArena Multi-Turn | 1454 | 1222 |
| EQ-Bench Creative Writing | 1794 | — |
| EQ-Bench 4 | 1236 | — |
| LiveBench Language | — | 23.3% |

## FAQ

### Is Claude Sonnet 5 better than Qwen2.5-Coder-32B?

Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 33.4 on the Noometry Index. Qwen2.5-Coder-32B costs 5.4× less per token, which makes it the better buy when Claude Sonnet 5's lead doesn't matter for your workload.

### Which is cheaper, Claude Sonnet 5 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; Claude Sonnet 5 lists at $2 and $10.

### Is Claude Sonnet 5 or Qwen2.5-Coder-32B better for coding?

Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 22.6 in the Noometry coding category.

### Which has the bigger context window?

Claude Sonnet 5 does, with 1M tokens against 33K.

### How many benchmarks do Claude Sonnet 5 and Qwen2.5-Coder-32B share?

13 benchmarks have published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and Qwen2.5-Coder-32B has 31.