# GLM-4.7 vs Mixtral 8x22B

> GLM-4.7 is the stronger model overall, scoring 42.0 to 27.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-7-vs-mixtral-8x22b
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. GLM-4.7 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-4.7 leads 47.0 to 15.1.
- The biggest single-benchmark swing is GPQA Diamond: 83.3% for GLM-4.7 and 34.1% for Mixtral 8x22B.
- GLM-4.7 is cheaper at $0.60 / $2.20 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- GLM-4.7 accepts more context: 205K tokens versus 64K.

## Snapshot

| | GLM-4.7 | Mixtral 8x22B |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 42.0 | 27.1 |
| Rank | 124 | 333 |
| Context | 205K | 64K |
| Input $/M | $0.60 | $2 |
| Output $/M | $2.20 | $6 |
| Weights | Open | Open |

## Coding

- GLM-4.7: 44.0 (#79)
- Mixtral 8x22B: 24.2 (#329)

| Benchmark | GLM-4.7 | Mixtral 8x22B |
|---|---|---|
| LMArena Coding | 1454 | 1166 |
| LMArena WebDev | 1435 | — |
| SciCode | 45.1% | — |
| WeirdML | — | 3.2% |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| ALE-Bench | 399.48 | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |

## Agentic & Tool Use

- GLM-4.7: 26.5 (#103)
- Mixtral 8x22B: 23.1 (#127)

| Benchmark | GLM-4.7 | Mixtral 8x22B |
|---|---|---|
| Terminal-Bench | 33.4% | — |
| Cybench | — | 7.5% |
| Vending-Bench 2 | 2,377 | — |

## Reasoning

- GLM-4.7: 24.3 (#164)
- Mixtral 8x22B: 19.9 (#248)

| Benchmark | GLM-4.7 | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1443 | 1150 |
| Epoch Capabilities Index | 143.51 | 122.03 |
| SimpleBench | 47.7% | — |
| CritPt | 1.7% | — |
| Chess Puzzles | 6% | — |
| DTBench | — | 55.1% |
| ForecastBench | — | 56.3 |

## Math

- GLM-4.7: 38.6 (#135)
- Mixtral 8x22B: 22.9 (#275)

| Benchmark | GLM-4.7 | Mixtral 8x22B |
|---|---|---|
| LMArena Math | 1423 | 1184 |
| OTIS Mock AIME 2024-2025 | 83.3% | — |
| ProofBench | 6% | — |
| Omni-MATH | — | 16.3% |
| MATH Level 5 | — | 24.2% |
| FrontierMath (Feb 2025 set) | 2.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- GLM-4.7: 47.0 (#80)
- Mixtral 8x22B: 15.1 (#293)

| Benchmark | GLM-4.7 | Mixtral 8x22B |
|---|---|---|
| GPQA Diamond | 83.3% | 34.1% |
| LMArena Expert | 1424 | 1113 |
| SimpleQA Verified | 32.2% | — |
| MMLU-Pro | — | 46% |
| Vectara Hallucination Rate | 11.7% | — |
| GPQA (HELM) | — | 33.4% |
| MMLU | — | 77.8% |

## Multilingual

- GLM-4.7: 52.8 (#79)
- Mixtral 8x22B: 32.8 (#255)

| Benchmark | GLM-4.7 | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1417 | 1128 |
| LMArena Chinese | 1495 | 1116 |
| LMArena French | 1432 | 1166 |
| LMArena German | 1424 | 1141 |
| LMArena Japanese | 1439 | 1037 |
| LMArena Korean | 1399 | 1057 |
| LMArena Russian | 1423 | 1158 |
| LMArena Spanish | 1434 | 1151 |

## Instruction Following

- GLM-4.7: 74.4 (#95)
- Mixtral 8x22B: 57.7 (#266)

| Benchmark | GLM-4.7 | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1411 | 1147 |
| IFEval | — | 72.4% |

## Long Context

- GLM-4.7: 42.8 (#116)
- Mixtral 8x22B: 34.7 (#247)

| Benchmark | GLM-4.7 | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1432 | 1144 |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |

## Writing & Preference

- GLM-4.7: 60.9 (#93)
- Mixtral 8x22B: 36.9 (#262)

| Benchmark | GLM-4.7 | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1435 | 1162 |
| LMArena Creative Writing | 1401 | 1141 |
| LMArena Multi-Turn | 1446 | 1130 |
| EQ-Bench Creative Writing | 1413 | — |
| WildBench | — | 71.1% |

## FAQ

### Is GLM-4.7 better than Mixtral 8x22B?

GLM-4.7 is the stronger model overall, scoring 42.0 to 27.1 on the Noometry Index.

### Which is cheaper, GLM-4.7 or Mixtral 8x22B?

GLM-4.7 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-4.7 or Mixtral 8x22B better for coding?

GLM-4.7 scores higher on coding benchmarks: 44.0 versus 24.2 in the Noometry coding category.

### Which has the bigger context window?

GLM-4.7 does, with 205K tokens against 64K.

### How many benchmarks do GLM-4.7 and Mixtral 8x22B share?

19 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and Mixtral 8x22B has 34.