# GLM-5.1 vs Magistral Medium

> GLM-5.1 is the stronger model overall, scoring 47.8 to 35.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-5-1-vs-magistral-medium
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. GLM-5.1 scores higher in 8 categories and Magistral Medium in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.1 leads 39.1 to 8.6.
- GLM-5.1 is cheaper at $1.40 / $4.40 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Magistral Medium accepts more context: 262K tokens versus 200K.

## Snapshot

| | GLM-5.1 | Magistral Medium |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 47.8 | 35.2 |
| Rank | 59 | 227 |
| Context | 200K | 262K |
| Input $/M | $1.40 | $2 |
| Output $/M | $4.40 | $5 |
| Weights | Open | Open |

## Coding

- GLM-5.1: 48.7 (#55)
- Magistral Medium: 39.1 (#161)

| Benchmark | GLM-5.1 | Magistral Medium |
|---|---|---|
| SciCode | 43.8% | 39.2% |
| LMArena Coding | 1485 | 1319 |
| SWE-bench Verified | 74.2% | — |
| LMArena WebDev | 1508 | — |
| WeirdML | 57.1% | — |
| ALE-Bench | 887.1 | — |

## Agentic & Tool Use

- GLM-5.1: 24.9 (#113)
- Magistral Medium: —

| Benchmark | GLM-5.1 | Magistral Medium |
|---|---|---|
| APEX-Agents | 40.9% | — |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |

## Reasoning

- GLM-5.1: 39.1 (#60)
- Magistral Medium: 8.6 (#348)

| Benchmark | GLM-5.1 | Magistral Medium |
|---|---|---|
| CritPt | 4.6% | 0.3% |
| LMArena Hard Prompts | 1472 | 1267 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | 55.1% | — |
| Kagi LLM Benchmark | — | 16.2% |
| NYT Connections (extended) | 77.7% | — |
| ARC-AGI-1 | — | 6.1% |
| Chess Puzzles | 19% | — |
| Thematic Generalization | 69.8% | — |
| Epoch Capabilities Index | 149.84 | — |

## Math

- GLM-5.1: 49.7 (#60)
- Magistral Medium: 35.1 (#189)

| Benchmark | GLM-5.1 | Magistral Medium |
|---|---|---|
| LMArena Math | 1473 | 1250 |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| OTIS Mock AIME 2024-2025 | 93.3% | — |
| ProofBench | 22.2% | — |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |

## Knowledge

- GLM-5.1: 54.9 (#50)
- Magistral Medium: 33.5 (#202)

| Benchmark | GLM-5.1 | Magistral Medium |
|---|---|---|
| LMArena Expert | 1476 | 1223 |
| GPQA Diamond | 89.9% | — |
| SimpleQA Verified | 34% | — |

## Multilingual

- GLM-5.1: 55.0 (#36)
- Magistral Medium: 39.6 (#224)

| Benchmark | GLM-5.1 | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1447 | 1232 |
| LMArena Chinese | 1515 | 1227 |
| LMArena French | 1474 | 1267 |
| LMArena German | 1465 | 1248 |
| LMArena Japanese | 1434 | 1175 |
| LMArena Korean | 1418 | 1125 |
| LMArena Russian | 1454 | 1224 |
| LMArena Spanish | 1469 | 1271 |

## Instruction Following

- GLM-5.1: 76.3 (#42)
- Magistral Medium: 66.0 (#211)

| Benchmark | GLM-5.1 | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1451 | 1254 |

## Long Context

- GLM-5.1: 44.9 (#53)
- Magistral Medium: 39.3 (#183)

| Benchmark | GLM-5.1 | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1466 | 1295 |

## Writing & Preference

- GLM-5.1: 66.9 (#31)
- Magistral Medium: 46.3 (#219)

| Benchmark | GLM-5.1 | Magistral Medium |
|---|---|---|
| LMArena Text | 1461 | 1255 |
| LMArena Creative Writing | 1453 | 1245 |
| LMArena Multi-Turn | 1472 | 1275 |
| EQ-Bench Creative Writing | 1592 | — |

## FAQ

### Is GLM-5.1 better than Magistral Medium?

GLM-5.1 is the stronger model overall, scoring 47.8 to 35.2 on the Noometry Index.

### Which is cheaper, GLM-5.1 or Magistral Medium?

GLM-5.1 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; Magistral Medium lists at $2 and $5.

### Is GLM-5.1 or Magistral Medium better for coding?

GLM-5.1 scores higher on coding benchmarks: 48.7 versus 39.1 in the Noometry coding category.

### Which has the bigger context window?

Magistral Medium does, with 262K tokens against 200K.

### How many benchmarks do GLM-5.1 and Magistral Medium share?

19 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Magistral Medium has 22.