# Hy3 vs Qwen2.5 72B Instruct

> Hy3 is the stronger model overall, scoring 44.2 to 31.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/hy3-vs-qwen2-5-72b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Hy3 scores higher in 8 categories and Qwen2.5 72B Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Hy3 leads 40.1 to 19.3.
- Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- Hy3 accepts more context: 262K tokens versus 131K.

## Snapshot

| | Hy3 | Qwen2.5 72B Instruct |
|---|---|---|
| Provider | Tencent | Alibaba (Qwen) |
| Noometry Index | 44.2 | 31.9 |
| Rank | 79 | 267 |
| Context | 262K | 131K |
| Input $/M | $0.0825 | $1.40 |
| Output $/M | $0.33 | $5.60 |
| Weights | Open | Open |

## Coding

- Hy3: 46.8 (#63)
- Qwen2.5 72B Instruct: 33.2 (#260)

| Benchmark | Hy3 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1464 | 1292 |
| LMArena WebDev | 1508 | — |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |

## Agentic & Tool Use

- Hy3: —
- Qwen2.5 72B Instruct: 22.1 (#133)

| Benchmark | Hy3 | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |

## Reasoning

- Hy3: 26.1 (#136)
- Qwen2.5 72B Instruct: 22.3 (#199)

| Benchmark | Hy3 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1271 |
| NYT Connections (extended) | 41.2% | — |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| Epoch Capabilities Index | — | 129 |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |

## Math

- Hy3: 40.1 (#93)
- Qwen2.5 72B Instruct: 19.3 (#287)

| Benchmark | Hy3 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Math | 1475 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |

## Knowledge

- Hy3: 40.8 (#114)
- Qwen2.5 72B Instruct: 27.0 (#253)

| Benchmark | Hy3 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Expert | 1460 | 1245 |
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |

## Multilingual

- Hy3: 53.5 (#65)
- Qwen2.5 72B Instruct: 41.0 (#213)

| Benchmark | Hy3 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1426 | 1252 |
| LMArena Chinese | 1493 | 1272 |
| LMArena French | 1461 | 1280 |
| LMArena German | 1439 | 1234 |
| LMArena Japanese | 1392 | 1180 |
| LMArena Korean | 1395 | 1188 |
| LMArena Russian | 1432 | 1264 |
| LMArena Spanish | 1456 | 1256 |

## Instruction Following

- Hy3: 75.1 (#70)
- Qwen2.5 72B Instruct: 65.5 (#221)

| Benchmark | Hy3 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1426 | 1254 |
| IFEval | — | 80.6% |

## Long Context

- Hy3: 44.1 (#75)
- Qwen2.5 72B Instruct: 38.9 (#188)

| Benchmark | Hy3 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1442 | 1282 |

## Writing & Preference

- Hy3: 62.2 (#81)
- Qwen2.5 72B Instruct: 46.7 (#215)

| Benchmark | Hy3 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1439 | 1269 |
| LMArena Creative Writing | 1402 | 1221 |
| LMArena Multi-Turn | 1436 | 1272 |
| WildBench | — | 80.2% |

## FAQ

### Is Hy3 better than Qwen2.5 72B Instruct?

Hy3 is the stronger model overall, scoring 44.2 to 31.9 on the Noometry Index.

### Which is cheaper, Hy3 or Qwen2.5 72B Instruct?

Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.

### Is Hy3 or Qwen2.5 72B Instruct better for coding?

Hy3 scores higher on coding benchmarks: 46.8 versus 33.2 in the Noometry coding category.

### Which has the bigger context window?

Hy3 does, with 262K tokens against 131K.

### How many benchmarks do Hy3 and Qwen2.5 72B Instruct share?

17 benchmarks have published results for both models. Hy3 has 19 scored results on Noometry and Qwen2.5 72B Instruct has 43.