# Codestral vs Grok 4.20 Multi-Agent

> Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 30.6 on the Noometry Index. Codestral costs 3.5× less per token, which makes it the better buy when Grok 4.20 Multi-Agent's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/codestral-vs-grok-4-20-multi-agent
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where Grok 4.20 Multi-Agent leads 43.9 to 19.8.
- Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 Multi-Agent.
- Grok 4.20 Multi-Agent accepts more context: 1M tokens versus 256K.

## Snapshot

| | Codestral | Grok 4.20 Multi-Agent |
|---|---|---|
| Provider | Mistral AI | xAI |
| Noometry Index | 30.6 | 46.2 |
| Rank | 290 | 65 |
| Context | 256K | 1M |
| Input $/M | $0.30 | $1.25 |
| Output $/M | $0.90 | $2.50 |
| Weights | Proprietary | Proprietary |

## Coding

- Codestral: 27.3 (#321)
- Grok 4.20 Multi-Agent: 43.0 (#92)

| Benchmark | Codestral | Grok 4.20 Multi-Agent |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1457 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |

## Agentic & Tool Use

- Codestral: —
- Grok 4.20 Multi-Agent: —

| Benchmark | Codestral | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Search | — | 1204 |

## Reasoning

- Codestral: 19.8 (#251)
- Grok 4.20 Multi-Agent: 43.9 (#48)

| Benchmark | Codestral | Grok 4.20 Multi-Agent |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| NYT Connections (extended) | — | 89.6% |
| LMArena Hard Prompts | — | 1448 |

## Math

- Codestral: —
- Grok 4.20 Multi-Agent: 39.4 (#104)

| Benchmark | Codestral | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Math | — | 1442 |

## Knowledge

- Codestral: —
- Grok 4.20 Multi-Agent: 40.4 (#119)

| Benchmark | Codestral | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Expert | — | 1445 |

## Multimodal

- Codestral: —
- Grok 4.20 Multi-Agent: 40.5 (#48)

| Benchmark | Codestral | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Vision | — | 1259 |

## Multilingual

- Codestral: —
- Grok 4.20 Multi-Agent: 54.4 (#43)

| Benchmark | Codestral | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Non-English | — | 1440 |
| LMArena Chinese | — | 1475 |
| LMArena French | — | 1466 |
| LMArena German | — | 1456 |
| LMArena Japanese | — | 1405 |
| LMArena Korean | — | 1416 |
| LMArena Russian | — | 1457 |
| LMArena Spanish | — | 1447 |

## Instruction Following

- Codestral: —
- Grok 4.20 Multi-Agent: 74.8 (#84)

| Benchmark | Codestral | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Instruction Following | — | 1420 |

## Long Context

- Codestral: —
- Grok 4.20 Multi-Agent: 43.7 (#88)

| Benchmark | Codestral | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Longer Query | — | 1431 |

## Writing & Preference

- Codestral: —
- Grok 4.20 Multi-Agent: 64.0 (#59)

| Benchmark | Codestral | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Text | — | 1450 |
| LMArena Creative Writing | — | 1436 |
| LMArena Multi-Turn | — | 1452 |

## FAQ

### Is Codestral better than Grok 4.20 Multi-Agent?

Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 30.6 on the Noometry Index. Codestral costs 3.5× less per token, which makes it the better buy when Grok 4.20 Multi-Agent's lead doesn't matter for your workload.

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

Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; Grok 4.20 Multi-Agent lists at $1.25 and $2.50.

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

Grok 4.20 Multi-Agent scores higher on coding benchmarks: 43.0 versus 27.3 in the Noometry coding category.

### Which has the bigger context window?

Grok 4.20 Multi-Agent does, with 1M tokens against 256K.

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

0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Grok 4.20 Multi-Agent has 20.