# GLM-5.1 vs Mixtral 8x22B

> GLM-5.1 is the stronger model overall, scoring 47.6 to 26.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-5-1-vs-mixtral-8x22b
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. GLM-5.1 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-5.1 leads 55.0 to 15.1.
- The biggest single-benchmark swing is GPQA Diamond: 89.9% for GLM-5.1 and 34.1% for Mixtral 8x22B.
- GLM-5.1 is cheaper at $1.40 / $4.40 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- GLM-5.1 accepts more context: 200K tokens versus 64K.

## Snapshot

| | GLM-5.1 | Mixtral 8x22B |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 47.6 | 26.7 |
| Rank | 51 | 330 |
| Context | 200K | 64K |
| Input $/M | $1.40 | $2 |
| Output $/M | $4.40 | $6 |
| Weights | Open | Open |

## Coding

- GLM-5.1: 48.5 (#52)
- Mixtral 8x22B: 23.8 (#324)

| Benchmark | GLM-5.1 | Mixtral 8x22B |
|---|---|---|
| WeirdML | 57.1% | 3.2% |
| LMArena Coding | 1486 | 1166 |
| SWE-bench Verified | 74.2% | — |
| LMArena WebDev | 1509 | — |
| SciCode | 43.8% | — |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| ALE-Bench | 887.1 | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |

## Agentic & Tool Use

- GLM-5.1: 24.8 (#106)
- Mixtral 8x22B: 22.8 (#119)

| Benchmark | GLM-5.1 | Mixtral 8x22B |
|---|---|---|
| APEX-Agents | 40.9% | — |
| Cybench | — | 7.5% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |

## Reasoning

- GLM-5.1: 38.2 (#57)
- Mixtral 8x22B: 19.1 (#246)

| Benchmark | GLM-5.1 | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1472 | 1150 |
| Epoch Capabilities Index | 149.86 | 122 |
| SimpleBench | 55.1% | — |
| NYT Connections (extended) | 77.7% | — |
| CritPt | 4.6% | — |
| Chess Puzzles | 19% | — |
| Thematic Generalization | 69.8% | — |
| DTBench | — | 55.1% |
| ForecastBench | — | 56.3 |

## Math

- GLM-5.1: 49.0 (#48)
- Mixtral 8x22B: 21.2 (#271)

| Benchmark | GLM-5.1 | Mixtral 8x22B |
|---|---|---|
| LMArena Math | 1472 | 1184 |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| OTIS Mock AIME 2024-2025 | 93.3% | — |
| ProofBench | 22.2% | — |
| Omni-MATH | — | 16.3% |
| MATH Level 5 | — | 24.2% |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |

## Knowledge

- GLM-5.1: 55.0 (#45)
- Mixtral 8x22B: 15.1 (#288)

| Benchmark | GLM-5.1 | Mixtral 8x22B |
|---|---|---|
| GPQA Diamond | 89.9% | 34.1% |
| LMArena Expert | 1477 | 1113 |
| SimpleQA Verified | 34% | — |
| MMLU-Pro | — | 46% |
| GPQA (HELM) | — | 33.4% |
| MMLU | — | 77.8% |

## Multilingual

- GLM-5.1: 55.2 (#34)
- Mixtral 8x22B: 32.9 (#250)

| Benchmark | GLM-5.1 | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1448 | 1128 |
| LMArena Chinese | 1516 | 1116 |
| LMArena French | 1478 | 1165 |
| LMArena German | 1466 | 1141 |
| LMArena Japanese | 1436 | 1037 |
| LMArena Korean | 1423 | 1056 |
| LMArena Russian | 1453 | 1158 |
| LMArena Spanish | 1467 | 1150 |

## Instruction Following

- GLM-5.1: 76.5 (#41)
- Mixtral 8x22B: 57.9 (#261)

| Benchmark | GLM-5.1 | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1451 | 1147 |
| IFEval | — | 72.4% |

## Long Context

- GLM-5.1: 44.9 (#51)
- Mixtral 8x22B: 34.6 (#242)

| Benchmark | GLM-5.1 | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1467 | 1144 |

## Writing & Preference

- GLM-5.1: 67.2 (#29)
- Mixtral 8x22B: 37.1 (#257)

| Benchmark | GLM-5.1 | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1462 | 1162 |
| LMArena Creative Writing | 1454 | 1141 |
| LMArena Multi-Turn | 1473 | 1130 |
| EQ-Bench Creative Writing | 1592 | — |
| WildBench | — | 71.1% |

## FAQ

### Is GLM-5.1 better than Mixtral 8x22B?

GLM-5.1 is the stronger model overall, scoring 47.6 to 26.7 on the Noometry Index.

### Which is cheaper, GLM-5.1 or Mixtral 8x22B?

GLM-5.1 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; Mixtral 8x22B lists at $2 and $6.

### Is GLM-5.1 or Mixtral 8x22B better for coding?

GLM-5.1 scores higher on coding benchmarks: 48.5 versus 23.8 in the Noometry coding category.

### Which has the bigger context window?

GLM-5.1 does, with 200K tokens against 64K.

### How many benchmarks do GLM-5.1 and Mixtral 8x22B share?

20 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Mixtral 8x22B has 34.