# Grok 4.20 Multi-Agent vs Magistral Medium

> Grok 4.20 Multi-Agent is the stronger model overall, scoring 45.5 to 34.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-4-20-multi-agent-vs-magistral-medium
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Grok 4.20 Multi-Agent 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 Grok 4.20 Multi-Agent leads 42.4 to 8.7.
- Grok 4.20 Multi-Agent is cheaper at $1.25 / $2.50 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Grok 4.20 Multi-Agent accepts more context: 1M tokens versus 128K.
- Magistral Medium has downloadable open weights; the other is API-only.

## Snapshot

| | Grok 4.20 Multi-Agent | Magistral Medium |
|---|---|---|
| Provider | xAI | Mistral AI |
| Noometry Index | 45.5 | 34.8 |
| Rank | 62 | 224 |
| Context | 1M | 128K |
| Input $/M | $1.25 | $2 |
| Output $/M | $2.50 | $5 |
| Weights | Proprietary | Open |

## Coding

- Grok 4.20 Multi-Agent: 42.4 (#91)
- Magistral Medium: 38.6 (#161)

| Benchmark | Grok 4.20 Multi-Agent | Magistral Medium |
|---|---|---|
| LMArena Coding | 1458 | 1319 |
| SciCode | — | 39.2% |

## Agentic & Tool Use

- Grok 4.20 Multi-Agent: —
- Magistral Medium: —

| Benchmark | Grok 4.20 Multi-Agent | Magistral Medium |
|---|---|---|
| LMArena Search | 1204 | — |

## Reasoning

- Grok 4.20 Multi-Agent: 42.4 (#44)
- Magistral Medium: 8.7 (#342)

| Benchmark | Grok 4.20 Multi-Agent | Magistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1448 | 1267 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 16.2% |
| NYT Connections (extended) | 89.6% | — |
| ARC-AGI-1 | — | 6.1% |
| CritPt | — | 0.3% |

## Math

- Grok 4.20 Multi-Agent: 36.6 (#106)
- Magistral Medium: 32.4 (#187)

| Benchmark | Grok 4.20 Multi-Agent | Magistral Medium |
|---|---|---|
| LMArena Math | 1441 | 1249 |

## Knowledge

- Grok 4.20 Multi-Agent: 39.7 (#116)
- Magistral Medium: 32.9 (#199)

| Benchmark | Grok 4.20 Multi-Agent | Magistral Medium |
|---|---|---|
| LMArena Expert | 1445 | 1222 |

## Multimodal

- Grok 4.20 Multi-Agent: 39.8 (#44)
- Magistral Medium: —

| Benchmark | Grok 4.20 Multi-Agent | Magistral Medium |
|---|---|---|
| LMArena Vision | 1259 | — |

## Multilingual

- Grok 4.20 Multi-Agent: 54.6 (#40)
- Magistral Medium: 39.8 (#219)

| Benchmark | Grok 4.20 Multi-Agent | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1440 | 1232 |
| LMArena Chinese | 1475 | 1225 |
| LMArena French | 1467 | 1268 |
| LMArena German | 1456 | 1248 |
| LMArena Japanese | 1405 | 1176 |
| LMArena Korean | 1416 | 1125 |
| LMArena Russian | 1457 | 1224 |
| LMArena Spanish | 1447 | 1269 |

## Instruction Following

- Grok 4.20 Multi-Agent: 75.0 (#80)
- Magistral Medium: 66.2 (#207)

| Benchmark | Grok 4.20 Multi-Agent | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1420 | 1254 |

## Long Context

- Grok 4.20 Multi-Agent: 43.7 (#84)
- Magistral Medium: 39.3 (#178)

| Benchmark | Grok 4.20 Multi-Agent | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1430 | 1295 |

## Writing & Preference

- Grok 4.20 Multi-Agent: 64.1 (#57)
- Magistral Medium: 46.5 (#214)

| Benchmark | Grok 4.20 Multi-Agent | Magistral Medium |
|---|---|---|
| LMArena Text | 1450 | 1255 |
| LMArena Creative Writing | 1435 | 1245 |
| LMArena Multi-Turn | 1451 | 1275 |

## FAQ

### Is Grok 4.20 Multi-Agent better than Magistral Medium?

Grok 4.20 Multi-Agent is the stronger model overall, scoring 45.5 to 34.8 on the Noometry Index.

### Which is cheaper, Grok 4.20 Multi-Agent or Magistral Medium?

Grok 4.20 Multi-Agent is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; Magistral Medium lists at $2 and $5.

### Is Grok 4.20 Multi-Agent or Magistral Medium better for coding?

Grok 4.20 Multi-Agent scores higher on coding benchmarks: 42.4 versus 38.6 in the Noometry coding category.

### Which has the bigger context window?

Grok 4.20 Multi-Agent does, with 1M tokens against 128K.

### How many benchmarks do Grok 4.20 Multi-Agent and Magistral Medium share?

17 benchmarks have published results for both models. Grok 4.20 Multi-Agent has 20 scored results on Noometry and Magistral Medium has 22.