# Claude Haiku 5.5 vs Qwen3 Max

> Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 43.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-haiku-5-5-vs-qwen3-max
- Last updated: 2026-10-10
- Shared benchmarks: 6

## Summary

- They share 6 benchmarks with published results for both. Claude Haiku 5.5 scores higher in 4 categories and Qwen3 Max in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Haiku 5.5 leads 73.6 to 38.7.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 75.1% for Claude Haiku 5.5 and 18.9% for Qwen3 Max.
- Claude Haiku 5.5 is cheaper at $0.10 / $0.50 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
- Claude Haiku 5.5 accepts more context: 1M tokens versus 262K.

## Snapshot

| | Claude Haiku 5.5 | Qwen3 Max |
|---|---|---|
| Provider | Anthropic | Alibaba (Qwen) |
| Noometry Index | 49.5 | 43.7 |
| Rank | 52 | 87 |
| Context | 1M | 262K |
| Input $/M | $0.10 | $1.20 |
| Output $/M | $0.50 | $6 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude Haiku 5.5: 49.2 (#50)
- Qwen3 Max: 43.0 (#93)

| Benchmark | Claude Haiku 5.5 | Qwen3 Max |
|---|---|---|
| LMArena WebDev | 1587 | — |
| LMArena Coding | — | 1456 |
| ALE-Bench | — | 370.45 |

## Agentic & Tool Use

- Claude Haiku 5.5: —
- Qwen3 Max: —

| Benchmark | Claude Haiku 5.5 | Qwen3 Max |
|---|---|---|
| Vending-Bench 2 | — | 71.56 |

## Reasoning

- Claude Haiku 5.5: 35.2 (#69)
- Qwen3 Max: 22.6 (#190)

| Benchmark | Claude Haiku 5.5 | Qwen3 Max |
|---|---|---|
| NYT Connections (extended) | 65.7% | 30.1% |
| Mystery Game Puzzles | 30% | 5% |
| Kagi LLM Benchmark | — | 72.5% |
| Chess Puzzles | — | 4% |
| LMArena Hard Prompts | — | 1448 |
| DTBench | — | 82.1% |
| LMCA | — | 28.3% |
| Epoch Capabilities Index | — | 142.38 |

## Math

- Claude Haiku 5.5: 73.6 (#18)
- Qwen3 Max: 38.7 (#131)

| Benchmark | Claude Haiku 5.5 | Qwen3 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | 75.1% | 18.9% |
| OTIS Mock AIME 2024-2025 | 98.9% | 73.3% |
| FrontierMath Tier 4 | 46.3% | — |
| LMArena Math | — | 1446 |
| MATH Level 5 | — | 97.1% |

## Knowledge

- Claude Haiku 5.5: 50.8 (#70)
- Qwen3 Max: 48.1 (#78)

| Benchmark | Claude Haiku 5.5 | Qwen3 Max |
|---|---|---|
| GPQA Diamond | 89.6% | 72.6% |
| SimpleQA Verified | 23.8% | 48.7% |
| LMArena Expert | — | 1455 |

## Multimodal

- Claude Haiku 5.5: 43.7 (#21)
- Qwen3 Max: —

| Benchmark | Claude Haiku 5.5 | Qwen3 Max |
|---|---|---|
| Furniture Assembly | 47.5% | — |

## Multilingual

- Claude Haiku 5.5: —
- Qwen3 Max: 53.7 (#62)

| Benchmark | Claude Haiku 5.5 | Qwen3 Max |
|---|---|---|
| LMArena Non-English | — | 1429 |
| LMArena Chinese | — | 1478 |
| LMArena French | — | 1449 |
| LMArena German | — | 1463 |
| LMArena Japanese | — | 1397 |
| LMArena Korean | — | 1399 |
| LMArena Russian | — | 1428 |
| LMArena Spanish | — | 1462 |

## Instruction Following

- Claude Haiku 5.5: —
- Qwen3 Max: 74.8 (#87)

| Benchmark | Claude Haiku 5.5 | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | — | 1419 |

## Long Context

- Claude Haiku 5.5: —
- Qwen3 Max: 41.6 (#134)

| Benchmark | Claude Haiku 5.5 | Qwen3 Max |
|---|---|---|
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 14.5% |
| LMArena Longer Query | — | 1438 |

## Writing & Preference

- Claude Haiku 5.5: —
- Qwen3 Max: 62.4 (#76)

| Benchmark | Claude Haiku 5.5 | Qwen3 Max |
|---|---|---|
| LMArena Text | — | 1439 |
| LMArena Creative Writing | — | 1402 |
| LMArena Multi-Turn | — | 1446 |

## FAQ

### Is Claude Haiku 5.5 better than Qwen3 Max?

Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 43.7 on the Noometry Index.

### Which is cheaper, Claude Haiku 5.5 or Qwen3 Max?

Claude Haiku 5.5 is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; Qwen3 Max lists at $1.20 and $6.

### Is Claude Haiku 5.5 or Qwen3 Max better for coding?

Claude Haiku 5.5 scores higher on coding benchmarks: 49.2 versus 43.0 in the Noometry coding category.

### Which has the bigger context window?

Claude Haiku 5.5 does, with 1M tokens against 262K.

### How many benchmarks do Claude Haiku 5.5 and Qwen3 Max share?

6 benchmarks have published results for both models. Claude Haiku 5.5 has 9 scored results on Noometry and Qwen3 Max has 33.