# GLM-4.5 vs Mixtral 8x22B

> GLM-4.5 is the stronger model overall, scoring 41.4 to 26.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-5-vs-mixtral-8x22b
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. GLM-4.5 scores higher in 8 categories and Mixtral 8x22B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.5 leads 57.7 to 37.1.
- The biggest single-benchmark swing is WeirdML: 40.6% for GLM-4.5 and 3.2% for Mixtral 8x22B.
- GLM-4.5 is cheaper at $0.60 / $2.20 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- GLM-4.5 accepts more context: 131K tokens versus 64K.

## Snapshot

| | GLM-4.5 | Mixtral 8x22B |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 41.4 | 26.7 |
| Rank | 125 | 330 |
| Context | 131K | 64K |
| Input $/M | $0.60 | $2 |
| Output $/M | $2.20 | $6 |
| Weights | Open | Open |

## Coding

- GLM-4.5: 41.1 (#121)
- Mixtral 8x22B: 23.8 (#324)

| Benchmark | GLM-4.5 | Mixtral 8x22B |
|---|---|---|
| WeirdML | 40.6% | 3.2% |
| LMArena Coding | 1434 | 1166 |
| SWE-bench Verified (bash only) | 54.2% | — |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| ALE-Bench | 344.82 | — |
| AlgoTune | 1.52 | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |

## Agentic & Tool Use

- GLM-4.5: —
- Mixtral 8x22B: 22.8 (#119)

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

## Reasoning

- GLM-4.5: 27.7 (#99)
- Mixtral 8x22B: 19.1 (#246)

| Benchmark | GLM-4.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1430 | 1150 |
| Kagi LLM Benchmark | 57.9% | — |
| DTBench | — | 55.1% |
| Epoch Capabilities Index | — | 122 |
| ForecastBench | — | 56.3 |

## Math

- GLM-4.5: 36.3 (#119)
- Mixtral 8x22B: 21.2 (#271)

| Benchmark | GLM-4.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Math | 1427 | 1184 |
| Omni-MATH | — | 16.3% |
| MATH Level 5 | — | 24.2% |

## Knowledge

- GLM-4.5: 35.5 (#172)
- Mixtral 8x22B: 15.1 (#288)

| Benchmark | GLM-4.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Expert | 1433 | 1113 |
| GPQA Diamond | — | 34.1% |
| Humanity's Last Exam | 8.3% | — |
| MMLU-Pro | — | 46% |
| Confabulations | 11.3% | — |
| GPQA (HELM) | — | 33.4% |
| MMLU | — | 77.8% |

## Multilingual

- GLM-4.5: 53.0 (#74)
- Mixtral 8x22B: 32.9 (#250)

| Benchmark | GLM-4.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1417 | 1128 |
| LMArena Chinese | 1465 | 1116 |
| LMArena French | 1423 | 1165 |
| LMArena German | 1406 | 1141 |
| LMArena Japanese | 1416 | 1037 |
| LMArena Korean | 1382 | 1056 |
| LMArena Russian | 1414 | 1158 |
| LMArena Spanish | 1454 | 1150 |

## Instruction Following

- GLM-4.5: 74.3 (#100)
- Mixtral 8x22B: 57.9 (#261)

| Benchmark | GLM-4.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1405 | 1147 |
| IFEval | — | 72.4% |

## Long Context

- GLM-4.5: 38.2 (#196)
- Mixtral 8x22B: 34.6 (#242)

| Benchmark | GLM-4.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1413 | 1144 |
| Fiction.LiveBench | 58.3% | — |

## Writing & Preference

- GLM-4.5: 57.7 (#121)
- Mixtral 8x22B: 37.1 (#257)

| Benchmark | GLM-4.5 | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1430 | 1162 |
| LMArena Creative Writing | 1395 | 1141 |
| LMArena Multi-Turn | 1415 | 1130 |
| Short-Story Creative Writing | 73.4% | — |
| EQ-Bench Creative Writing | 1343 | — |
| WildBench | — | 71.1% |

## FAQ

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

GLM-4.5 is the stronger model overall, scoring 41.4 to 26.7 on the Noometry Index.

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

GLM-4.5 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Mixtral 8x22B lists at $2 and $6.

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

GLM-4.5 scores higher on coding benchmarks: 41.1 versus 23.8 in the Noometry coding category.

### Which has the bigger context window?

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

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

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