# Command A vs Mixtral 8x22B

> Command A is the stronger model overall, scoring 36.5 to 27.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/command-a-vs-mixtral-8x22b
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Command A scores higher in 8 categories and Mixtral 8x22B in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Command A leads 37.1 to 15.1.
- The biggest single-benchmark swing is DTBench: 61.3% for Command A and 55.1% for Mixtral 8x22B.
- Mixtral 8x22B is cheaper at $2 / $6 per million input/output tokens, against $2.50 / $10 for Command A.
- Command A accepts more context: 256K tokens versus 64K.

## Snapshot

| | Command A | Mixtral 8x22B |
|---|---|---|
| Provider | Cohere | Mistral AI |
| Noometry Index | 36.5 | 27.1 |
| Rank | 215 | 333 |
| Context | 256K | 64K |
| Input $/M | $2.50 | $2 |
| Output $/M | $10 | $6 |
| Weights | Open | Open |

## Coding

- Command A: 27.2 (#322)
- Mixtral 8x22B: 24.2 (#329)

| Benchmark | Command A | Mixtral 8x22B |
|---|---|---|
| LMArena Coding | 1330 | 1166 |
| Aider Polyglot | 12% | — |
| WeirdML | — | 3.2% |
| BigCodeBench Instruct | — | 40.6% |
| BigCodeBench Complete | — | 50.2% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |

## Agentic & Tool Use

- Command A: 35.9 (#40)
- Mixtral 8x22B: 23.1 (#127)

| Benchmark | Command A | Mixtral 8x22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
| Cybench | — | 7.5% |

## Reasoning

- Command A: 18.3 (#283)
- Mixtral 8x22B: 19.9 (#248)

| Benchmark | Command A | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1150 |
| DTBench | 61.3% | 55.1% |
| Kagi LLM Benchmark | 28.8% | — |
| LMCA | 10.3% | — |
| Epoch Capabilities Index | — | 122.03 |
| ForecastBench | — | 56.3 |

## Math

- Command A: 36.2 (#171)
- Mixtral 8x22B: 22.9 (#275)

| Benchmark | Command A | Mixtral 8x22B |
|---|---|---|
| LMArena Math | 1300 | 1184 |
| Omni-MATH | — | 16.3% |
| MATH Level 5 | — | 24.2% |

## Knowledge

- Command A: 37.1 (#159)
- Mixtral 8x22B: 15.1 (#293)

| Benchmark | Command A | Mixtral 8x22B |
|---|---|---|
| LMArena Expert | 1295 | 1113 |
| GPQA Diamond | — | 34.1% |
| MMLU-Pro | — | 46% |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | — | 33.4% |
| MMLU | — | 77.8% |

## Multilingual

- Command A: 45.3 (#170)
- Mixtral 8x22B: 32.8 (#255)

| Benchmark | Command A | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1313 | 1128 |
| LMArena Chinese | 1327 | 1116 |
| LMArena French | 1351 | 1166 |
| LMArena German | 1341 | 1141 |
| LMArena Japanese | 1285 | 1037 |
| LMArena Korean | 1285 | 1057 |
| LMArena Russian | 1314 | 1158 |
| LMArena Spanish | 1347 | 1151 |

## Instruction Following

- Command A: 69.1 (#177)
- Mixtral 8x22B: 57.7 (#266)

| Benchmark | Command A | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1309 | 1147 |
| IFEval | — | 72.4% |

## Long Context

- Command A: 40.6 (#151)
- Mixtral 8x22B: 34.7 (#247)

| Benchmark | Command A | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1334 | 1144 |

## Writing & Preference

- Command A: 47.6 (#208)
- Mixtral 8x22B: 36.9 (#262)

| Benchmark | Command A | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1331 | 1162 |
| LMArena Creative Writing | 1319 | 1141 |
| LMArena Multi-Turn | 1339 | 1130 |
| EQ-Bench Creative Writing | 1145 | — |
| WildBench | — | 71.1% |

## FAQ

### Is Command A better than Mixtral 8x22B?

Command A is the stronger model overall, scoring 36.5 to 27.1 on the Noometry Index.

### Which is cheaper, Command A or Mixtral 8x22B?

Mixtral 8x22B is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; Command A lists at $2.50 and $10.

### Is Command A or Mixtral 8x22B better for coding?

Command A scores higher on coding benchmarks: 27.2 versus 24.2 in the Noometry coding category.

### Which has the bigger context window?

Command A does, with 256K tokens against 64K.

### How many benchmarks do Command A and Mixtral 8x22B share?

18 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Mixtral 8x22B has 34.