# Claude 3.5 Haiku vs Qwen Max

> Qwen Max is the stronger model overall, scoring 34.7 to 29.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-3-5-haiku-vs-qwen-max
- Last updated: 2026-10-12
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 1 category and Qwen Max in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen Max leads 30.3 to 18.7.
- The biggest single-benchmark swing is MATH Level 5: 46.4% for Claude 3.5 Haiku and 67.2% for Qwen Max.

## Snapshot

| | Claude 3.5 Haiku | Qwen Max |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 29.2 | 34.7 |
| Rank | 315 | 230 |
| Context | — | 33K |
| Input $/M | — | $1.60 |
| Output $/M | — | $6.40 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 3.5 Haiku: 32.9 (#265)
- Qwen Max: 30.7 (#292)

| Benchmark | Claude 3.5 Haiku | Qwen Max |
|---|---|---|
| Aider Polyglot | 28% | 21.8% |
| LMArena Coding | 1286 | 1288 |
| SciCode | 27.4% | — |
| WeirdML | 30.7% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 51.4% | — |
| BigCodeBench Complete | 59% | — |
| CadEval | 32% | — |

## Agentic & Tool Use

- Claude 3.5 Haiku: 28.0 (#95)
- Qwen Max: —

| Benchmark | Claude 3.5 Haiku | Qwen Max |
|---|---|---|
| BALROG | 19.3% | — |

## Reasoning

- Claude 3.5 Haiku: 17.7 (#290)
- Qwen Max: 25.1 (#151)

| Benchmark | Claude 3.5 Haiku | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1269 |
| CritPt | 0% | — |
| LiveBench Reasoning | 28.1% | — |
| DTBench | 56.7% | — |
| LiveBench Data Analysis | 48.5% | — |
| Epoch Capabilities Index | 127.15 | — |
| LiveBench | 43.5% | — |

## Math

- Claude 3.5 Haiku: 14.7 (#300)
- Qwen Max: 22.3 (#276)

| Benchmark | Claude 3.5 Haiku | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 16.1% |
| LMArena Math | 1244 | 1275 |
| MATH Level 5 | 46.4% | 67.2% |
| FrontierMath (Feb 2025 set) | 0.3% | 1% |
| Omni-MATH | 22.4% | — |
| LiveBench Math | 35.5% | — |

## Knowledge

- Claude 3.5 Haiku: 18.7 (#281)
- Qwen Max: 30.3 (#228)

| Benchmark | Claude 3.5 Haiku | Qwen Max |
|---|---|---|
| GPQA Diamond | 38.1% | 56.1% |
| LMArena Expert | 1208 | 1248 |
| MMLU-Pro | 60.5% | — |
| Confabulations | 36.7% | — |
| GPQA (HELM) | 36.3% | — |
| MMLU | 74.3% | — |

## Multimodal

- Claude 3.5 Haiku: 26.8 (#117)
- Qwen Max: —

| Benchmark | Claude 3.5 Haiku | Qwen Max |
|---|---|---|
| LMArena Vision | 1092 | — |
| GeoBench | 34% | — |

## Multilingual

- Claude 3.5 Haiku: 40.0 (#218)
- Qwen Max: 41.8 (#202)

| Benchmark | Claude 3.5 Haiku | Qwen Max |
|---|---|---|
| LMArena Non-English | 1238 | 1263 |
| LMArena Chinese | 1229 | 1254 |
| LMArena French | 1264 | 1330 |
| LMArena German | 1237 | 1254 |
| LMArena Japanese | 1175 | 1205 |
| LMArena Korean | 1173 | 1142 |
| LMArena Russian | 1253 | 1274 |
| LMArena Spanish | 1261 | 1290 |

## Instruction Following

- Claude 3.5 Haiku: 62.9 (#234)
- Qwen Max: 66.5 (#208)

| Benchmark | Claude 3.5 Haiku | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1241 | 1262 |
| LiveBench Instruction Following | 61.9% | — |
| IFEval | 79.2% | — |

## Long Context

- Claude 3.5 Haiku: 38.3 (#200)
- Qwen Max: 39.4 (#180)

| Benchmark | Claude 3.5 Haiku | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1261 | 1288 |
| Fiction.LiveBench | — | 66.7% |

## Writing & Preference

- Claude 3.5 Haiku: 42.7 (#234)
- Qwen Max: 47.8 (#205)

| Benchmark | Claude 3.5 Haiku | Qwen Max |
|---|---|---|
| LMArena Text | 1255 | 1282 |
| LMArena Creative Writing | 1233 | 1248 |
| LMArena Multi-Turn | 1265 | 1277 |
| Short-Story Creative Writing | 73.5% | — |
| EQ-Bench Creative Writing | 1146 | — |
| WildBench | 76% | — |
| LiveBench Language | 35.4% | — |

## FAQ

### Is Claude 3.5 Haiku better than Qwen Max?

Qwen Max is the stronger model overall, scoring 34.7 to 29.2 on the Noometry Index.

### Is Claude 3.5 Haiku or Qwen Max better for coding?

Claude 3.5 Haiku scores higher on coding benchmarks: 32.9 versus 30.7 in the Noometry coding category.

### How many benchmarks do Claude 3.5 Haiku and Qwen Max share?

22 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Qwen Max has 23.