# GLM-4.5-Air vs Magistral Medium

> GLM-4.5-Air is the stronger model overall, scoring 38.9 to 35.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-5-air-vs-magistral-medium
- Last updated: 2026-10-12
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. GLM-4.5-Air scores higher in 7 categories and Magistral Medium in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-4.5-Air leads 24.1 to 8.6.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 43% for GLM-4.5-Air and 16.2% for Magistral Medium.
- GLM-4.5-Air is cheaper at $0.20 / $1.10 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Magistral Medium accepts more context: 262K tokens versus 131K.

## Snapshot

| | GLM-4.5-Air | Magistral Medium |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 38.9 | 35.2 |
| Rank | 177 | 227 |
| Context | 131K | 262K |
| Input $/M | $0.20 | $2 |
| Output $/M | $1.10 | $5 |
| Weights | Open | Open |

## Coding

- GLM-4.5-Air: 33.3 (#259)
- Magistral Medium: 39.1 (#161)

| Benchmark | GLM-4.5-Air | Magistral Medium |
|---|---|---|
| LMArena Coding | 1397 | 1319 |
| SciCode | — | 39.2% |
| GSO | 2.9% | — |

## Reasoning

- GLM-4.5-Air: 24.1 (#166)
- Magistral Medium: 8.6 (#348)

| Benchmark | GLM-4.5-Air | Magistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 43% | 16.2% |
| LMArena Hard Prompts | 1379 | 1267 |
| ARC-AGI-2 | — | 0% |
| ARC-AGI-1 | — | 6.1% |
| CritPt | — | 0.3% |
| ForecastBench | 59.2 | — |

## Math

- GLM-4.5-Air: 36.2 (#170)
- Magistral Medium: 35.1 (#189)

| Benchmark | GLM-4.5-Air | Magistral Medium |
|---|---|---|
| LMArena Math | 1396 | 1250 |
| Omni-MATH | 39.1% | — |

## Knowledge

- GLM-4.5-Air: 35.0 (#191)
- Magistral Medium: 33.5 (#202)

| Benchmark | GLM-4.5-Air | Magistral Medium |
|---|---|---|
| LMArena Expert | 1370 | 1223 |
| Humanity's Last Exam | 8.1% | — |
| MMLU-Pro | 76.2% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 59.4% | — |

## Multilingual

- GLM-4.5-Air: 49.1 (#135)
- Magistral Medium: 39.6 (#224)

| Benchmark | GLM-4.5-Air | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1366 | 1232 |
| LMArena Chinese | 1426 | 1227 |
| LMArena French | 1399 | 1267 |
| LMArena German | 1377 | 1248 |
| LMArena Japanese | 1348 | 1175 |
| LMArena Korean | 1308 | 1125 |
| LMArena Russian | 1373 | 1224 |
| LMArena Spanish | 1386 | 1271 |

## Instruction Following

- GLM-4.5-Air: 69.6 (#171)
- Magistral Medium: 66.0 (#211)

| Benchmark | GLM-4.5-Air | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1354 | 1254 |
| IFEval | 81.2% | — |

## Long Context

- GLM-4.5-Air: 41.6 (#135)
- Magistral Medium: 39.3 (#183)

| Benchmark | GLM-4.5-Air | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1366 | 1295 |

## Writing & Preference

- GLM-4.5-Air: 55.9 (#139)
- Magistral Medium: 46.3 (#219)

| Benchmark | GLM-4.5-Air | Magistral Medium |
|---|---|---|
| LMArena Text | 1384 | 1255 |
| LMArena Creative Writing | 1343 | 1245 |
| LMArena Multi-Turn | 1371 | 1275 |
| WildBench | 78.9% | — |

## FAQ

### Is GLM-4.5-Air better than Magistral Medium?

GLM-4.5-Air is the stronger model overall, scoring 38.9 to 35.2 on the Noometry Index.

### Which is cheaper, GLM-4.5-Air or Magistral Medium?

GLM-4.5-Air is cheaper. It lists at $0.20 per million input tokens and $1.10 per million output tokens; Magistral Medium lists at $2 and $5.

### Is GLM-4.5-Air or Magistral Medium better for coding?

Magistral Medium scores higher on coding benchmarks: 39.1 versus 33.3 in the Noometry coding category.

### Which has the bigger context window?

Magistral Medium does, with 262K tokens against 131K.

### How many benchmarks do GLM-4.5-Air and Magistral Medium share?

18 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Magistral Medium has 22.