# Claude Haiku 4.5 vs Qwen Max

> Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 34.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-haiku-4-5-vs-qwen-max
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 7 categories and Qwen Max in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Haiku 4.5 leads 44.9 to 22.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 66.7% for Claude Haiku 4.5 and 16.1% for Qwen Max.
- Claude Haiku 4.5 is cheaper at $1 / $5 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
- Claude Haiku 4.5 accepts more context: 200K tokens versus 33K.

## Snapshot

| | Claude Haiku 4.5 | Qwen Max |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 39.5 | 34.7 |
| Rank | 165 | 230 |
| Context | 200K | 33K |
| Input $/M | $1 | $1.60 |
| Output $/M | $5 | $6.40 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Haiku 4.5: 44.0 (#78)
- Qwen Max: 30.7 (#292)

| Benchmark | Claude Haiku 4.5 | Qwen Max |
|---|---|---|
| LMArena Coding | 1453 | 1288 |
| SWE-bench Verified (bash only) | 66.6% | — |
| Aider Polyglot | — | 21.8% |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| WeirdML | 45.4% | — |
| ALE-Bench | 653.48 | — |

## Agentic & Tool Use

- Claude Haiku 4.5: 33.6 (#52)
- Qwen Max: —

| Benchmark | Claude Haiku 4.5 | Qwen Max |
|---|---|---|
| Terminal-Bench | 35.5% | — |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
| Vending-Bench 2 | 458.89 | — |

## Reasoning

- Claude Haiku 4.5: 15.1 (#320)
- Qwen Max: 25.1 (#151)

| Benchmark | Claude Haiku 4.5 | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1269 |
| ARC-AGI-2 | 4% | — |
| NYT Connections (extended) | 14.3% | — |
| ARC-AGI-1 | 47.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | 8% | — |
| DTBench | 73.6% | — |
| LMCA | 30.9% | — |
| Epoch Capabilities Index | 142.41 | — |
| ForecastBench | 61.4 | — |

## Math

- Claude Haiku 4.5: 44.9 (#78)
- Qwen Max: 22.3 (#276)

| Benchmark | Claude Haiku 4.5 | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.7% | 16.1% |
| LMArena Math | 1396 | 1275 |
| MATH Level 5 | 96.4% | 67.2% |
| FrontierMath (Feb 2025 set) | 5.9% | 1% |
| Omni-MATH | 56.1% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- Claude Haiku 4.5: 37.7 (#153)
- Qwen Max: 30.3 (#228)

| Benchmark | Claude Haiku 4.5 | Qwen Max |
|---|---|---|
| GPQA Diamond | 71.2% | 56.1% |
| LMArena Expert | 1442 | 1248 |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |

## Multimodal

- Claude Haiku 4.5: 26.8 (#118)
- Qwen Max: —

| Benchmark | Claude Haiku 4.5 | Qwen Max |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |

## Multilingual

- Claude Haiku 4.5: 49.9 (#129)
- Qwen Max: 41.8 (#202)

| Benchmark | Claude Haiku 4.5 | Qwen Max |
|---|---|---|
| LMArena Non-English | 1377 | 1263 |
| LMArena Chinese | 1417 | 1254 |
| LMArena French | 1408 | 1330 |
| LMArena German | 1375 | 1254 |
| LMArena Japanese | 1339 | 1205 |
| LMArena Korean | 1347 | 1142 |
| LMArena Russian | 1381 | 1274 |
| LMArena Spanish | 1420 | 1290 |

## Instruction Following

- Claude Haiku 4.5: 71.4 (#149)
- Qwen Max: 66.5 (#208)

| Benchmark | Claude Haiku 4.5 | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1414 | 1262 |
| IFEval | 80.1% | — |

## Long Context

- Claude Haiku 4.5: 43.6 (#92)
- Qwen Max: 39.4 (#180)

| Benchmark | Claude Haiku 4.5 | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1427 | 1288 |
| Fiction.LiveBench | — | 66.7% |

## Writing & Preference

- Claude Haiku 4.5: 57.9 (#123)
- Qwen Max: 47.8 (#205)

| Benchmark | Claude Haiku 4.5 | Qwen Max |
|---|---|---|
| LMArena Text | 1396 | 1282 |
| LMArena Creative Writing | 1372 | 1248 |
| LMArena Multi-Turn | 1409 | 1277 |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |

## FAQ

### Is Claude Haiku 4.5 better than Qwen Max?

Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 34.7 on the Noometry Index.

### Which is cheaper, Claude Haiku 4.5 or Qwen Max?

Claude Haiku 4.5 is cheaper. It lists at $1 per million input tokens and $5 per million output tokens; Qwen Max lists at $1.60 and $6.40.

### Is Claude Haiku 4.5 or Qwen Max better for coding?

Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 30.7 in the Noometry coding category.

### Which has the bigger context window?

Claude Haiku 4.5 does, with 200K tokens against 33K.

### How many benchmarks do Claude Haiku 4.5 and Qwen Max share?

21 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Qwen Max has 23.