# Hy3 vs Qwen Max

> Hy3 is the stronger model overall, scoring 43.6 to 34.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/hy3-vs-qwen-max
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Hy3 scores higher in 8 categories and Qwen Max in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Hy3 leads 37.4 to 21.0.
- Hy3 is cheaper at $0.13 / $0.53 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
- Hy3 accepts more context: 262K tokens versus 33K.
- Hy3 has downloadable open weights; the other is API-only.

## Snapshot

| | Hy3 | Qwen Max |
|---|---|---|
| Provider | Tencent | Alibaba (Qwen) |
| Noometry Index | 43.6 | 34.4 |
| Rank | 79 | 226 |
| Context | 262K | 33K |
| Input $/M | $0.13 | $1.60 |
| Output $/M | $0.53 | $6.40 |
| Weights | Open | Proprietary |

## Coding

- Hy3: 46.6 (#60)
- Qwen Max: 30.3 (#288)

| Benchmark | Hy3 | Qwen Max |
|---|---|---|
| LMArena Coding | 1465 | 1288 |
| Aider Polyglot | — | 21.8% |
| LMArena WebDev | 1509 | — |

## Reasoning

- Hy3: 25.0 (#134)
- Qwen Max: 24.1 (#154)

| Benchmark | Hy3 | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1449 | 1270 |
| NYT Connections (extended) | 41.2% | — |

## Math

- Hy3: 37.4 (#98)
- Qwen Max: 21.0 (#272)

| Benchmark | Hy3 | Qwen Max |
|---|---|---|
| LMArena Math | 1475 | 1275 |
| OTIS Mock AIME 2024-2025 | — | 16.1% |
| MATH Level 5 | — | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |

## Knowledge

- Hy3: 40.2 (#108)
- Qwen Max: 30.3 (#222)

| Benchmark | Hy3 | Qwen Max |
|---|---|---|
| LMArena Expert | 1461 | 1248 |
| GPQA Diamond | — | 56.1% |

## Multilingual

- Hy3: 53.7 (#60)
- Qwen Max: 42.0 (#197)

| Benchmark | Hy3 | Qwen Max |
|---|---|---|
| LMArena Non-English | 1427 | 1263 |
| LMArena Chinese | 1496 | 1254 |
| LMArena French | 1461 | 1329 |
| LMArena Korean | 1390 | 1141 |
| LMArena Russian | 1435 | 1274 |
| LMArena Spanish | 1448 | 1290 |
| LMArena German | — | 1254 |
| LMArena Japanese | — | 1205 |

## Instruction Following

- Hy3: 75.3 (#68)
- Qwen Max: 66.7 (#203)

| Benchmark | Hy3 | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1425 | 1262 |

## Long Context

- Hy3: 44.1 (#70)
- Qwen Max: 39.4 (#175)

| Benchmark | Hy3 | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1443 | 1289 |
| Fiction.LiveBench | — | 66.7% |

## Writing & Preference

- Hy3: 62.5 (#75)
- Qwen Max: 48.0 (#200)

| Benchmark | Hy3 | Qwen Max |
|---|---|---|
| LMArena Text | 1442 | 1282 |
| LMArena Creative Writing | 1399 | 1248 |
| LMArena Multi-Turn | 1436 | 1277 |

## FAQ

### Is Hy3 better than Qwen Max?

Hy3 is the stronger model overall, scoring 43.6 to 34.4 on the Noometry Index.

### Which is cheaper, Hy3 or Qwen Max?

Hy3 is cheaper. It lists at $0.13 per million input tokens and $0.53 per million output tokens; Qwen Max lists at $1.60 and $6.40.

### Is Hy3 or Qwen Max better for coding?

Hy3 scores higher on coding benchmarks: 46.6 versus 30.3 in the Noometry coding category.

### Which has the bigger context window?

Hy3 does, with 262K tokens against 33K.

### How many benchmarks do Hy3 and Qwen Max share?

15 benchmarks have published results for both models. Hy3 has 17 scored results on Noometry and Qwen Max has 23.