# Claude 3 Haiku vs Qwen2.5-Coder-32B

> Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 to 25.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-haiku-vs-qwen2-5-coder-32b
- Last updated: 2026-10-12
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Claude 3 Haiku scores higher in 1 category and Qwen2.5-Coder-32B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2.5-Coder-32B leads 33.3 to 9.8.
- The biggest single-benchmark swing is BigCodeBench Instruct: 39.4% for Claude 3 Haiku and 49% for Qwen2.5-Coder-32B.
- Qwen2.5-Coder-32B has downloadable open weights; the other is API-only.

## Snapshot

| | Claude 3 Haiku | Qwen2.5-Coder-32B |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 25.9 | 33.4 |
| Rank | 340 | 245 |
| Context | — | 33K |
| Input $/M | — | $0.66 |
| Output $/M | — | $1 |
| Weights | Proprietary | Open |

## Coding

- Claude 3 Haiku: 26.4 (#325)
- Qwen2.5-Coder-32B: 22.6 (#333)

| Benchmark | Claude 3 Haiku | Qwen2.5-Coder-32B |
|---|---|---|
| BigCodeBench Instruct | 39.4% | 49% |
| LMArena Coding | 1199 | 1276 |
| BigCodeBench Complete | 50.1% | 58% |
| HumanEval+ | 68.9% | 87.2% |
| MBPP+ | 68.8% | 77% |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| WeirdML | 9.8% | — |
| LiveBench Coding | — | 56.9% |
| CadEval | 12% | — |

## Reasoning

- Claude 3 Haiku: 16.3 (#307)
- Qwen2.5-Coder-32B: 21.2 (#225)

| Benchmark | Claude 3 Haiku | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1251 |
| Epoch Capabilities Index | 118.35 | 119.49 |
| WinoGrande | 74.2% | 80.8% |
| Kagi LLM Benchmark | 34.2% | — |
| LiveBench Reasoning | — | 42.1% |
| DTBench | 50.1% | — |
| LiveBench Data Analysis | — | 49.9% |
| LMCA | 8.8% | — |
| ForecastBench | 53.2 | — |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |

## Math

- Claude 3 Haiku: 9.8 (#319)
- Qwen2.5-Coder-32B: 33.3 (#204)

| Benchmark | Claude 3 Haiku | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1188 | 1251 |
| OTIS Mock AIME 2024-2025 | 1.8% | — |
| LiveBench Math | — | 46.6% |
| MATH Level 5 | 14.9% | — |
| GSM8K | — | 93% |

## Knowledge

- Claude 3 Haiku: 17.3 (#285)
- Qwen2.5-Coder-32B: 33.4 (#203)

| Benchmark | Claude 3 Haiku | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1148 | 1221 |
| MMLU | 73.8% | 79.1% |
| GPQA Diamond | 36.3% | — |
| Confabulations | 34.2% | — |
| ARC (AI2) Challenge | — | 70.5% |

## Multimodal

- Claude 3 Haiku: 23.6 (#128)
- Qwen2.5-Coder-32B: —

| Benchmark | Claude 3 Haiku | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Vision | 950 | — |
| ScienceQA | 72% | — |

## Multilingual

- Claude 3 Haiku: 36.0 (#243)
- Qwen2.5-Coder-32B: 37.8 (#235)

| Benchmark | Claude 3 Haiku | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1178 | 1205 |
| LMArena Chinese | 1155 | 1222 |
| LMArena Russian | 1204 | 1228 |
| LMArena French | 1195 | — |
| LMArena German | 1174 | — |
| LMArena Japanese | 1102 | — |
| LMArena Korean | 1109 | — |
| LMArena Spanish | 1166 | — |

## Instruction Following

- Claude 3 Haiku: 61.3 (#247)
- Qwen2.5-Coder-32B: 61.4 (#245)

| Benchmark | Claude 3 Haiku | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1173 | 1223 |
| LiveBench Instruction Following | — | 58.7% |

## Long Context

- Claude 3 Haiku: 36.1 (#237)
- Qwen2.5-Coder-32B: 38.0 (#208)

| Benchmark | Claude 3 Haiku | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1190 | 1251 |

## Writing & Preference

- Claude 3 Haiku: 29.7 (#291)
- Qwen2.5-Coder-32B: 41.6 (#240)

| Benchmark | Claude 3 Haiku | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1195 | 1230 |
| LMArena Creative Writing | 1157 | 1174 |
| LMArena Multi-Turn | 1190 | 1222 |
| EQ-Bench Creative Writing | 717 | — |
| LiveBench Language | — | 23.3% |

## FAQ

### Is Claude 3 Haiku better than Qwen2.5-Coder-32B?

Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 to 25.9 on the Noometry Index.

### Is Claude 3 Haiku or Qwen2.5-Coder-32B better for coding?

Claude 3 Haiku scores higher on coding benchmarks: 26.4 versus 22.6 in the Noometry coding category.

### How many benchmarks do Claude 3 Haiku and Qwen2.5-Coder-32B share?

19 benchmarks have published results for both models. Claude 3 Haiku has 37 scored results on Noometry and Qwen2.5-Coder-32B has 31.