# GLM-4.5-Air vs Hy4 preview

> Hy4 preview is the stronger model overall, scoring 44.6 to 38.7 on the Noometry Index. GLM-4.5-Air costs 2.9× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/glm-4-5-air-vs-hy4-preview
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where Hy4 preview leads 54.5 to 33.8.
- GLM-4.5-Air is cheaper at $0.20 / $1.10 per million input/output tokens, against $0.83 / $2.50 for Hy4 preview.
- Hy4 preview accepts more context: 1.05M tokens versus 131K.

## Snapshot

| | GLM-4.5-Air | Hy4 preview |
|---|---|---|
| Provider | Z.ai (Zhipu) | Tencent |
| Noometry Index | 38.7 | 44.6 |
| Rank | 169 | 73 |
| Context | 131K | 1.05M |
| Input $/M | $0.20 | $0.83 |
| Output $/M | $1.10 | $2.50 |
| Weights | Open | Open |

## Coding

- GLM-4.5-Air: 34.5 (#225)
- Hy4 preview: 51.4 (#36)

| Benchmark | GLM-4.5-Air | Hy4 preview |
|---|---|---|
| LMArena WebDev | — | 1633 |
| GSO | 2.9% | — |
| LMArena Coding | 1397 | — |

## Reasoning

- GLM-4.5-Air: 23.3 (#166)
- Hy4 preview: 30.6 (#75)

| Benchmark | GLM-4.5-Air | Hy4 preview |
|---|---|---|
| Kagi LLM Benchmark | 43% | — |
| NYT Connections (extended) | — | 68.2% |
| LMArena Hard Prompts | 1379 | — |
| ForecastBench | 59.2 | — |

## Math

- GLM-4.5-Air: 33.8 (#166)
- Hy4 preview: 54.5 (#37)

| Benchmark | GLM-4.5-Air | Hy4 preview |
|---|---|---|
| ProofBench | — | 75% |
| Omni-MATH | 39.1% | — |
| LMArena Math | 1396 | — |

## Knowledge

- GLM-4.5-Air: 34.6 (#184)
- Hy4 preview: —

| Benchmark | GLM-4.5-Air | Hy4 preview |
|---|---|---|
| Humanity's Last Exam | 8.1% | — |
| MMLU-Pro | 76.2% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 59.4% | — |
| LMArena Expert | 1370 | — |

## Multilingual

- GLM-4.5-Air: 49.4 (#130)
- Hy4 preview: —

| Benchmark | GLM-4.5-Air | Hy4 preview |
|---|---|---|
| LMArena Non-English | 1366 | — |
| LMArena Chinese | 1427 | — |
| LMArena French | 1399 | — |
| LMArena German | 1376 | — |
| LMArena Japanese | 1348 | — |
| LMArena Korean | 1306 | — |
| LMArena Russian | 1373 | — |
| LMArena Spanish | 1385 | — |

## Instruction Following

- GLM-4.5-Air: 69.8 (#165)
- Hy4 preview: —

| Benchmark | GLM-4.5-Air | Hy4 preview |
|---|---|---|
| IFEval | 81.2% | — |
| LMArena Instruction Following | 1353 | — |

## Long Context

- GLM-4.5-Air: 41.6 (#130)
- Hy4 preview: —

| Benchmark | GLM-4.5-Air | Hy4 preview |
|---|---|---|
| LMArena Longer Query | 1367 | — |

## Writing & Preference

- GLM-4.5-Air: 56.1 (#134)
- Hy4 preview: —

| Benchmark | GLM-4.5-Air | Hy4 preview |
|---|---|---|
| LMArena Text | 1384 | — |
| LMArena Creative Writing | 1343 | — |
| WildBench | 78.9% | — |
| LMArena Multi-Turn | 1371 | — |

## FAQ

### Is GLM-4.5-Air better than Hy4 preview?

Hy4 preview is the stronger model overall, scoring 44.6 to 38.7 on the Noometry Index. GLM-4.5-Air costs 2.9× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.

### Which is cheaper, GLM-4.5-Air or Hy4 preview?

GLM-4.5-Air is cheaper. It lists at $0.20 per million input tokens and $1.10 per million output tokens; Hy4 preview lists at $0.83 and $2.50.

### Is GLM-4.5-Air or Hy4 preview better for coding?

Hy4 preview scores higher on coding benchmarks: 51.4 versus 34.5 in the Noometry coding category.

### Which has the bigger context window?

Hy4 preview does, with 1.05M tokens against 131K.

### How many benchmarks do GLM-4.5-Air and Hy4 preview share?

0 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Hy4 preview has 3.