# Command R vs Mixtral 8x22B

> Command R is the stronger model overall, scoring 31.4 to 27.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/command-r-vs-mixtral-8x22b
- Last updated: 2026-10-12
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Command R scores higher in 7 categories and Mixtral 8x22B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Command R leads 31.0 to 15.1.
- The biggest single-benchmark swing is DTBench: 46.4% for Command R and 55.1% for Mixtral 8x22B.
- Command R is cheaper at $0.15 / $0.60 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- Command R accepts more context: 128K tokens versus 64K.

## Snapshot

| | Command R | Mixtral 8x22B |
|---|---|---|
| Provider | Cohere | Mistral AI |
| Noometry Index | 31.4 | 27.1 |
| Rank | 272 | 333 |
| Context | 128K | 64K |
| Input $/M | $0.15 | $2 |
| Output $/M | $0.60 | $6 |
| Weights | Open | Open |

## Coding

- Command R: 29.3 (#306)
- Mixtral 8x22B: 24.2 (#329)

| Benchmark | Command R | Mixtral 8x22B |
|---|---|---|
| BigCodeBench Instruct | 37.1% | 40.6% |
| LMArena Coding | 1169 | 1166 |
| BigCodeBench Complete | 45.2% | 50.2% |
| WeirdML | — | 3.2% |
| LiveBench Coding | 17.9% | — |
| HumanEval+ | — | 72% |
| MBPP+ | — | 64.3% |

## Agentic & Tool Use

- Command R: —
- Mixtral 8x22B: 23.1 (#127)

| Benchmark | Command R | Mixtral 8x22B |
|---|---|---|
| Cybench | — | 7.5% |

## Reasoning

- Command R: 13.8 (#331)
- Mixtral 8x22B: 19.9 (#248)

| Benchmark | Command R | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1164 | 1150 |
| DTBench | 46.4% | 55.1% |
| LiveBench Reasoning | 21.9% | — |
| LiveBench Data Analysis | 33.3% | — |
| LMCA | 9.2% | — |
| Epoch Capabilities Index | — | 122.03 |
| ForecastBench | — | 56.3 |
| LiveBench | 27.5% | — |

## Math

- Command R: 28.0 (#246)
- Mixtral 8x22B: 22.9 (#275)

| Benchmark | Command R | Mixtral 8x22B |
|---|---|---|
| LMArena Math | 1155 | 1184 |
| Omni-MATH | — | 16.3% |
| LiveBench Math | 19.4% | — |
| MATH Level 5 | — | 24.2% |

## Knowledge

- Command R: 31.0 (#221)
- Mixtral 8x22B: 15.1 (#293)

| Benchmark | Command R | Mixtral 8x22B |
|---|---|---|
| LMArena Expert | 1138 | 1113 |
| MMLU | 65.2% | 77.8% |
| GPQA Diamond | — | 34.1% |
| MMLU-Pro | — | 46% |
| GPQA (HELM) | — | 33.4% |

## Multilingual

- Command R: 35.7 (#245)
- Mixtral 8x22B: 32.8 (#255)

| Benchmark | Command R | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 1174 | 1128 |
| LMArena Chinese | 1182 | 1116 |
| LMArena French | 1162 | 1166 |
| LMArena German | 1176 | 1141 |
| LMArena Japanese | 1143 | 1037 |
| LMArena Korean | 1163 | 1057 |
| LMArena Russian | 1174 | 1158 |
| LMArena Spanish | 1151 | 1151 |

## Instruction Following

- Command R: 58.1 (#261)
- Mixtral 8x22B: 57.7 (#266)

| Benchmark | Command R | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1167 | 1147 |
| LiveBench Instruction Following | 55.6% | — |
| IFEval | — | 72.4% |

## Long Context

- Command R: 36.3 (#231)
- Mixtral 8x22B: 34.7 (#247)

| Benchmark | Command R | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | 1198 | 1144 |

## Writing & Preference

- Command R: 38.2 (#254)
- Mixtral 8x22B: 36.9 (#262)

| Benchmark | Command R | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1187 | 1162 |
| LMArena Creative Writing | 1170 | 1141 |
| LMArena Multi-Turn | 1163 | 1130 |
| WildBench | — | 71.1% |
| LiveBench Language | 16.7% | — |

## FAQ

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

Command R is the stronger model overall, scoring 31.4 to 27.1 on the Noometry Index.

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

Command R is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Mixtral 8x22B lists at $2 and $6.

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

Command R scores higher on coding benchmarks: 29.3 versus 24.2 in the Noometry coding category.

### Which has the bigger context window?

Command R does, with 128K tokens against 64K.

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

21 benchmarks have published results for both models. Command R has 29 scored results on Noometry and Mixtral 8x22B has 34.