# Command A vs Magistral Medium

> Command A is the stronger model overall, scoring 35.9 to 34.8 on the Noometry Index. Magistral Medium costs 1.6× less per token, which makes it the better buy when Command A's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/command-a-vs-magistral-medium
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Command A scores higher in 7 categories and Magistral Medium in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Magistral Medium leads 38.6 to 26.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 28.8% for Command A and 16.2% for Magistral Medium.
- Magistral Medium is cheaper at $2 / $5 per million input/output tokens, against $2.50 / $10 for Command A.
- Command A accepts more context: 256K tokens versus 128K.

## Snapshot

| | Command A | Magistral Medium |
|---|---|---|
| Provider | Cohere | Mistral AI |
| Noometry Index | 35.9 | 34.8 |
| Rank | 212 | 224 |
| Context | 256K | 128K |
| Input $/M | $2.50 | $2 |
| Output $/M | $10 | $5 |
| Weights | Open | Open |

## Coding

- Command A: 26.8 (#317)
- Magistral Medium: 38.6 (#161)

| Benchmark | Command A | Magistral Medium |
|---|---|---|
| LMArena Coding | 1331 | 1319 |
| Aider Polyglot | 12% | — |
| SciCode | — | 39.2% |

## Agentic & Tool Use

- Command A: 35.7 (#36)
- Magistral Medium: —

| Benchmark | Command A | Magistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |

## Reasoning

- Command A: 17.7 (#276)
- Magistral Medium: 8.7 (#342)

| Benchmark | Command A | Magistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 28.8% | 16.2% |
| LMArena Hard Prompts | 1326 | 1267 |
| ARC-AGI-2 | — | 0% |
| ARC-AGI-1 | — | 6.1% |
| CritPt | — | 0.3% |
| DTBench | 61.3% | — |
| LMCA | 10.3% | — |

## Math

- Command A: 33.5 (#172)
- Magistral Medium: 32.4 (#187)

| Benchmark | Command A | Magistral Medium |
|---|---|---|
| LMArena Math | 1300 | 1249 |

## Knowledge

- Command A: 36.5 (#157)
- Magistral Medium: 32.9 (#199)

| Benchmark | Command A | Magistral Medium |
|---|---|---|
| LMArena Expert | 1295 | 1222 |
| Vectara Hallucination Rate | 9.3% | — |

## Multilingual

- Command A: 45.5 (#166)
- Magistral Medium: 39.8 (#219)

| Benchmark | Command A | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1313 | 1232 |
| LMArena Chinese | 1327 | 1225 |
| LMArena French | 1352 | 1268 |
| LMArena German | 1341 | 1248 |
| LMArena Japanese | 1283 | 1176 |
| LMArena Korean | 1285 | 1125 |
| LMArena Russian | 1314 | 1224 |
| LMArena Spanish | 1346 | 1269 |

## Instruction Following

- Command A: 69.3 (#172)
- Magistral Medium: 66.2 (#207)

| Benchmark | Command A | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1309 | 1254 |

## Long Context

- Command A: 40.6 (#147)
- Magistral Medium: 39.3 (#178)

| Benchmark | Command A | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1334 | 1295 |

## Writing & Preference

- Command A: 47.8 (#204)
- Magistral Medium: 46.5 (#214)

| Benchmark | Command A | Magistral Medium |
|---|---|---|
| LMArena Text | 1331 | 1255 |
| LMArena Creative Writing | 1319 | 1245 |
| LMArena Multi-Turn | 1338 | 1275 |
| EQ-Bench Creative Writing | 1145 | — |

## FAQ

### Is Command A better than Magistral Medium?

Command A is the stronger model overall, scoring 35.9 to 34.8 on the Noometry Index. Magistral Medium costs 1.6× less per token, which makes it the better buy when Command A's lead doesn't matter for your workload.

### Which is cheaper, Command A or Magistral Medium?

Magistral Medium is cheaper. It lists at $2 per million input tokens and $5 per million output tokens; Command A lists at $2.50 and $10.

### Is Command A or Magistral Medium better for coding?

Magistral Medium scores higher on coding benchmarks: 38.6 versus 26.8 in the Noometry coding category.

### Which has the bigger context window?

Command A does, with 256K tokens against 128K.

### How many benchmarks do Command A and Magistral Medium share?

18 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Magistral Medium has 22.