# GLM-4.6 vs Mistral Medium 3.5

> GLM-4.6 is the stronger model overall, scoring 40.9 to 39.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-4-6-vs-mistral-medium-3-5
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. GLM-4.6 scores higher in 6 categories and Mistral Medium 3.5 in 2 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-4.6 leads 23.1 to 16.6.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 47.4% for GLM-4.6 and 41.4% for Mistral Medium 3.5.
- GLM-4.6 is cheaper at $0.60 / $2.20 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
- Mistral Medium 3.5 accepts more context: 262K tokens versus 205K.

## Snapshot

| | GLM-4.6 | Mistral Medium 3.5 |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 40.9 | 39.6 |
| Rank | 132 | 151 |
| Context | 205K | 262K |
| Input $/M | $0.60 | $1.50 |
| Output $/M | $2.20 | $7.50 |
| Weights | Open | Open |

## Coding

- GLM-4.6: 39.9 (#137)
- Mistral Medium 3.5: 35.7 (#208)

| Benchmark | GLM-4.6 | Mistral Medium 3.5 |
|---|---|---|
| LMArena WebDev | 1339 | 1263 |
| LMArena Coding | 1449 | 1461 |
| SWE-bench Verified (bash only) | 55.4% | — |
| SciCode | 38.4% | — |
| ALE-Bench | 340.82 | — |

## Agentic & Tool Use

- GLM-4.6: 32.1 (#60)
- Mistral Medium 3.5: —

| Benchmark | GLM-4.6 | Mistral Medium 3.5 |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |

## Reasoning

- GLM-4.6: 23.1 (#168)
- Mistral Medium 3.5: 16.6 (#290)

| Benchmark | GLM-4.6 | Mistral Medium 3.5 |
|---|---|---|
| Kagi LLM Benchmark | 47.4% | 41.4% |
| LMArena Hard Prompts | 1440 | 1436 |
| NYT Connections (extended) | — | 12.9% |
| CritPt | 1.1% | — |
| Epoch Capabilities Index | — | 141.42 |

## Math

- GLM-4.6: 36.4 (#115)
- Mistral Medium 3.5: 36.4 (#113)

| Benchmark | GLM-4.6 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Math | 1431 | 1432 |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GLM-4.6: 39.6 (#118)
- Mistral Medium 3.5: 39.3 (#123)

| Benchmark | GLM-4.6 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Expert | 1432 | 1431 |
| Vectara Hallucination Rate | 9.5% | — |

## Multimodal

- GLM-4.6: —
- Mistral Medium 3.5: 37.6 (#64)

| Benchmark | GLM-4.6 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Vision | — | 1222 |

## Multilingual

- GLM-4.6: 53.6 (#62)
- Mistral Medium 3.5: 52.1 (#93)

| Benchmark | GLM-4.6 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Non-English | 1426 | 1405 |
| LMArena Chinese | 1500 | 1443 |
| LMArena French | 1459 | 1448 |
| LMArena German | 1447 | 1453 |
| LMArena Korean | 1401 | 1387 |
| LMArena Russian | 1418 | 1396 |
| LMArena Spanish | 1436 | 1406 |
| LMArena Japanese | 1394 | — |

## Instruction Following

- GLM-4.6: 74.5 (#93)
- Mistral Medium 3.5: 74.7 (#87)

| Benchmark | GLM-4.6 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Instruction Following | 1410 | 1414 |

## Long Context

- GLM-4.6: 43.4 (#91)
- Mistral Medium 3.5: 43.2 (#101)

| Benchmark | GLM-4.6 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Longer Query | 1423 | 1414 |

## Writing & Preference

- GLM-4.6: 61.3 (#86)
- Mistral Medium 3.5: 58.6 (#113)

| Benchmark | GLM-4.6 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Text | 1440 | 1421 |
| LMArena Creative Writing | 1411 | 1372 |
| LMArena Multi-Turn | 1427 | 1423 |
| EQ-Bench Creative Writing | 1411 | — |
| EQ-Bench 4 | — | 993 |

## FAQ

### Is GLM-4.6 better than Mistral Medium 3.5?

GLM-4.6 is the stronger model overall, scoring 40.9 to 39.6 on the Noometry Index.

### Which is cheaper, GLM-4.6 or Mistral Medium 3.5?

GLM-4.6 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

### Is GLM-4.6 or Mistral Medium 3.5 better for coding?

GLM-4.6 scores higher on coding benchmarks: 39.9 versus 35.7 in the Noometry coding category.

### Which has the bigger context window?

Mistral Medium 3.5 does, with 262K tokens against 205K.

### How many benchmarks do GLM-4.6 and Mistral Medium 3.5 share?

18 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Mistral Medium 3.5 has 22.