# GLM-4.5-Air vs Mixtral 8x22B

> GLM-4.5-Air is the stronger model overall, scoring 38.9 to 27.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-5-air-vs-mixtral-8x22b
- Last updated: 2026-10-12
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. GLM-4.5-Air scores higher in 8 categories and Mixtral 8x22B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.5-Air leads 35.0 to 15.1.
- The biggest single-benchmark swing is MMLU-Pro: 76.2% for GLM-4.5-Air and 46% for Mixtral 8x22B.
- GLM-4.5-Air is cheaper at $0.20 / $1.10 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- GLM-4.5-Air accepts more context: 131K tokens versus 64K.

## Snapshot

| | GLM-4.5-Air | Mixtral 8x22B |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 38.9 | 27.1 |
| Rank | 177 | 333 |
| Context | 131K | 64K |
| Input $/M | $0.20 | $2 |
| Output $/M | $1.10 | $6 |
| Weights | Open | Open |

## Coding

- GLM-4.5-Air: 33.3 (#259)
- Mixtral 8x22B: 24.2 (#329)

| Benchmark | GLM-4.5-Air | Mixtral 8x22B |
|---|---|---|
| LMArena Coding | 1397 | 1166 |
| GSO | 2.9% | — |
| WeirdML | — | 3.2% |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |

## Agentic & Tool Use

- GLM-4.5-Air: —
- Mixtral 8x22B: 23.1 (#127)

| Benchmark | GLM-4.5-Air | Mixtral 8x22B |
|---|---|---|
| Cybench | — | 7.5% |

## Reasoning

- GLM-4.5-Air: 24.1 (#166)
- Mixtral 8x22B: 19.9 (#248)

| Benchmark | GLM-4.5-Air | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1379 | 1150 |
| ForecastBench | 59.2 | 56.3 |
| Kagi LLM Benchmark | 43% | — |
| DTBench | — | 55.1% |
| Epoch Capabilities Index | — | 122.03 |

## Math

- GLM-4.5-Air: 36.2 (#170)
- Mixtral 8x22B: 22.9 (#275)

| Benchmark | GLM-4.5-Air | Mixtral 8x22B |
|---|---|---|
| Omni-MATH | 39.1% | 16.3% |
| LMArena Math | 1396 | 1184 |
| MATH Level 5 | — | 24.2% |

## Knowledge

- GLM-4.5-Air: 35.0 (#191)
- Mixtral 8x22B: 15.1 (#293)

| Benchmark | GLM-4.5-Air | Mixtral 8x22B |
|---|---|---|
| MMLU-Pro | 76.2% | 46% |
| GPQA (HELM) | 59.4% | 33.4% |
| LMArena Expert | 1370 | 1113 |
| GPQA Diamond | — | 34.1% |
| Humanity's Last Exam | 8.1% | — |
| Vectara Hallucination Rate | 9.3% | — |
| MMLU | — | 77.8% |

## Multilingual

- GLM-4.5-Air: 49.1 (#135)
- Mixtral 8x22B: 32.8 (#255)

| Benchmark | GLM-4.5-Air | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1366 | 1128 |
| LMArena Chinese | 1426 | 1116 |
| LMArena French | 1399 | 1166 |
| LMArena German | 1377 | 1141 |
| LMArena Japanese | 1348 | 1037 |
| LMArena Korean | 1308 | 1057 |
| LMArena Russian | 1373 | 1158 |
| LMArena Spanish | 1386 | 1151 |

## Instruction Following

- GLM-4.5-Air: 69.6 (#171)
- Mixtral 8x22B: 57.7 (#266)

| Benchmark | GLM-4.5-Air | Mixtral 8x22B |
|---|---|---|
| IFEval | 81.2% | 72.4% |
| LMArena Instruction Following | 1354 | 1147 |

## Long Context

- GLM-4.5-Air: 41.6 (#135)
- Mixtral 8x22B: 34.7 (#247)

| Benchmark | GLM-4.5-Air | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1366 | 1144 |

## Writing & Preference

- GLM-4.5-Air: 55.9 (#139)
- Mixtral 8x22B: 36.9 (#262)

| Benchmark | GLM-4.5-Air | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1384 | 1162 |
| LMArena Creative Writing | 1343 | 1141 |
| WildBench | 78.9% | 71.1% |
| LMArena Multi-Turn | 1371 | 1130 |

## FAQ

### Is GLM-4.5-Air better than Mixtral 8x22B?

GLM-4.5-Air is the stronger model overall, scoring 38.9 to 27.1 on the Noometry Index.

### Which is cheaper, GLM-4.5-Air or Mixtral 8x22B?

GLM-4.5-Air is cheaper. It lists at $0.20 per million input tokens and $1.10 per million output tokens; Mixtral 8x22B lists at $2 and $6.

### Is GLM-4.5-Air or Mixtral 8x22B better for coding?

GLM-4.5-Air scores higher on coding benchmarks: 33.3 versus 24.2 in the Noometry coding category.

### Which has the bigger context window?

GLM-4.5-Air does, with 131K tokens against 64K.

### How many benchmarks do GLM-4.5-Air and Mixtral 8x22B share?

23 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Mixtral 8x22B has 34.