# GLM-4.6 vs Mixtral 8x22B

> GLM-4.6 is the stronger model overall, scoring 41.4 to 27.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-6-vs-mixtral-8x22b
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. GLM-4.6 scores higher in 9 categories and Mixtral 8x22B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.6 leads 40.2 to 15.1.
- GLM-4.6 is cheaper at $0.60 / $2.20 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- GLM-4.6 accepts more context: 205K tokens versus 64K.

## Snapshot

| | GLM-4.6 | Mixtral 8x22B |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 41.4 | 27.1 |
| Rank | 135 | 333 |
| Context | 205K | 64K |
| Input $/M | $0.60 | $2 |
| Output $/M | $2.20 | $6 |
| Weights | Open | Open |

## Coding

- GLM-4.6: 40.1 (#148)
- Mixtral 8x22B: 24.2 (#329)

| Benchmark | GLM-4.6 | Mixtral 8x22B |
|---|---|---|
| LMArena Coding | 1449 | 1166 |
| SWE-bench Verified (bash only) | 55.4% | — |
| LMArena WebDev | 1340 | — |
| SciCode | 38.4% | — |
| WeirdML | — | 3.2% |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| ALE-Bench | 340.82 | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |

## Agentic & Tool Use

- GLM-4.6: 32.3 (#66)
- Mixtral 8x22B: 23.1 (#127)

| Benchmark | GLM-4.6 | Mixtral 8x22B |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |
| Cybench | — | 7.5% |

## Reasoning

- GLM-4.6: 23.7 (#172)
- Mixtral 8x22B: 19.9 (#248)

| Benchmark | GLM-4.6 | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1440 | 1150 |
| Kagi LLM Benchmark | 47.4% | — |
| CritPt | 1.1% | — |
| DTBench | — | 55.1% |
| Epoch Capabilities Index | — | 122.03 |
| ForecastBench | — | 56.3 |

## Math

- GLM-4.6: 39.1 (#111)
- Mixtral 8x22B: 22.9 (#275)

| Benchmark | GLM-4.6 | Mixtral 8x22B |
|---|---|---|
| LMArena Math | 1432 | 1184 |
| Omni-MATH | — | 16.3% |
| MATH Level 5 | — | 24.2% |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GLM-4.6: 40.2 (#124)
- Mixtral 8x22B: 15.1 (#293)

| Benchmark | GLM-4.6 | Mixtral 8x22B |
|---|---|---|
| LMArena Expert | 1431 | 1113 |
| GPQA Diamond | — | 34.1% |
| MMLU-Pro | — | 46% |
| Vectara Hallucination Rate | 9.5% | — |
| GPQA (HELM) | — | 33.4% |
| MMLU | — | 77.8% |

## Multilingual

- GLM-4.6: 53.5 (#66)
- Mixtral 8x22B: 32.8 (#255)

| Benchmark | GLM-4.6 | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1426 | 1128 |
| LMArena Chinese | 1499 | 1116 |
| LMArena French | 1459 | 1166 |
| LMArena German | 1447 | 1141 |
| LMArena Japanese | 1393 | 1037 |
| LMArena Korean | 1400 | 1057 |
| LMArena Russian | 1419 | 1158 |
| LMArena Spanish | 1436 | 1151 |

## Instruction Following

- GLM-4.6: 74.3 (#98)
- Mixtral 8x22B: 57.7 (#266)

| Benchmark | GLM-4.6 | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1410 | 1147 |
| IFEval | — | 72.4% |

## Long Context

- GLM-4.6: 43.4 (#94)
- Mixtral 8x22B: 34.7 (#247)

| Benchmark | GLM-4.6 | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1422 | 1144 |

## Writing & Preference

- GLM-4.6: 61.1 (#90)
- Mixtral 8x22B: 36.9 (#262)

| Benchmark | GLM-4.6 | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1440 | 1162 |
| LMArena Creative Writing | 1411 | 1141 |
| LMArena Multi-Turn | 1427 | 1130 |
| EQ-Bench Creative Writing | 1411 | — |
| WildBench | — | 71.1% |

## FAQ

### Is GLM-4.6 better than Mixtral 8x22B?

GLM-4.6 is the stronger model overall, scoring 41.4 to 27.1 on the Noometry Index.

### Which is cheaper, GLM-4.6 or Mixtral 8x22B?

GLM-4.6 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-4.6 or Mixtral 8x22B better for coding?

GLM-4.6 scores higher on coding benchmarks: 40.1 versus 24.2 in the Noometry coding category.

### Which has the bigger context window?

GLM-4.6 does, with 205K tokens against 64K.

### How many benchmarks do GLM-4.6 and Mixtral 8x22B share?

17 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Mixtral 8x22B has 34.