# GLM-5.2 vs Mistral Medium 3.5

> GLM-5.2 is the stronger model overall, scoring 51.1 to 40.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-5-2-vs-mistral-medium-3-5
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. GLM-5.2 scores higher in 8 categories and Mistral Medium 3.5 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.2 leads 42.3 to 17.3.
- The biggest single-benchmark swing is NYT Connections (extended): 74.3% for GLM-5.2 and 12.9% for Mistral Medium 3.5.
- GLM-5.2 is cheaper at $1.40 / $4.40 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
- GLM-5.2 accepts more context: 1M tokens versus 262K.

## Snapshot

| | GLM-5.2 | Mistral Medium 3.5 |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 51.1 | 40.2 |
| Rank | 44 | 152 |
| Context | 1M | 262K |
| Input $/M | $1.40 | $1.50 |
| Output $/M | $4.40 | $7.50 |
| Weights | Open | Open |

## Coding

- GLM-5.2: 51.3 (#41)
- Mistral Medium 3.5: 36.0 (#213)

| Benchmark | GLM-5.2 | Mistral Medium 3.5 |
|---|---|---|
| LMArena WebDev | 1603 | 1264 |
| LMArena Coding | 1485 | 1461 |
| SWE-bench Verified | 78.7% | — |
| DeepSWE | 43.8% | — |
| FrontierCode | 24.5% | — |
| SciCode | 50.5% | — |
| WeirdML | 70.1% | — |
| ALE-Bench | 1,047 | — |

## Agentic & Tool Use

- GLM-5.2: 32.4 (#63)
- Mistral Medium 3.5: —

| Benchmark | GLM-5.2 | Mistral Medium 3.5 |
|---|---|---|
| APEX-Agents | 45.2% | — |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 31.7% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 8,314 | — |

## Reasoning

- GLM-5.2: 42.3 (#52)
- Mistral Medium 3.5: 17.3 (#295)

| Benchmark | GLM-5.2 | Mistral Medium 3.5 |
|---|---|---|
| Kagi LLM Benchmark | 62.6% | 41.4% |
| NYT Connections (extended) | 74.3% | 12.9% |
| LMArena Hard Prompts | 1480 | 1436 |
| Epoch Capabilities Index | 151.78 | 141.35 |
| ARC-AGI-2 | 22.8% | — |
| SimpleBench | 58.8% | — |
| ARC-AGI-1 | 77% | — |
| CritPt | 20.9% | — |
| Chess Puzzles | 21% | — |
| EBR-Bench | 9.5% | — |
| Mystery Game Puzzles | 19% | — |
| DTBench | 93.6% | — |
| LMCA | 45.8% | — |
| Surface Evolver Bench | 55.6% | — |

## Math

- GLM-5.2: 55.7 (#43)
- Mistral Medium 3.5: 39.1 (#113)

| Benchmark | GLM-5.2 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Math | 1482 | 1431 |
| FrontierMath (Tiers 1-3) | 59.2% | — |
| FrontierMath Tier 4 | 29.3% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| OTIS Mock AIME 2024-2025 | 86.4% | — |
| ProofBench | 35% | — |

## Knowledge

- GLM-5.2: 57.1 (#40)
- Mistral Medium 3.5: 40.0 (#126)

| Benchmark | GLM-5.2 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Expert | 1486 | 1432 |
| GPQA Diamond | 91.9% | — |
| SimpleQA Verified | 34.2% | — |

## Multimodal

- GLM-5.2: —
- Mistral Medium 3.5: 38.3 (#65)

| Benchmark | GLM-5.2 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Vision | — | 1223 |

## Multilingual

- GLM-5.2: 55.8 (#26)
- Mistral Medium 3.5: 51.9 (#100)

| Benchmark | GLM-5.2 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Non-English | 1459 | 1404 |
| LMArena Chinese | 1519 | 1442 |
| LMArena French | 1479 | 1448 |
| LMArena German | 1468 | 1451 |
| LMArena Korean | 1445 | 1385 |
| LMArena Russian | 1466 | 1395 |
| LMArena Spanish | 1477 | 1409 |
| LMArena Japanese | 1451 | — |

## Instruction Following

- GLM-5.2: 76.9 (#34)
- Mistral Medium 3.5: 74.6 (#90)

| Benchmark | GLM-5.2 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Instruction Following | 1465 | 1415 |

## Long Context

- GLM-5.2: 45.3 (#43)
- Mistral Medium 3.5: 43.2 (#103)

| Benchmark | GLM-5.2 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Longer Query | 1479 | 1415 |

## Writing & Preference

- GLM-5.2: 70.4 (#21)
- Mistral Medium 3.5: 58.5 (#117)

| Benchmark | GLM-5.2 | Mistral Medium 3.5 |
|---|---|---|
| LMArena Text | 1470 | 1421 |
| LMArena Creative Writing | 1462 | 1374 |
| EQ-Bench 4 | 1222 | 993 |
| LMArena Multi-Turn | 1469 | 1423 |
| EQ-Bench Creative Writing | 1757 | — |

## FAQ

### Is GLM-5.2 better than Mistral Medium 3.5?

GLM-5.2 is the stronger model overall, scoring 51.1 to 40.2 on the Noometry Index.

### Which is cheaper, GLM-5.2 or Mistral Medium 3.5?

GLM-5.2 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

### Is GLM-5.2 or Mistral Medium 3.5 better for coding?

GLM-5.2 scores higher on coding benchmarks: 51.3 versus 36.0 in the Noometry coding category.

### Which has the bigger context window?

GLM-5.2 does, with 1M tokens against 262K.

### How many benchmarks do GLM-5.2 and Mistral Medium 3.5 share?

21 benchmarks have published results for both models. GLM-5.2 has 51 scored results on Noometry and Mistral Medium 3.5 has 22.