# Command R vs MiniMax-M2.1

> MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 31.4 on the Noometry Index. Command R costs 2.0× less per token, which makes it the better buy when MiniMax-M2.1's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/command-r-vs-minimax-m2-1
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Command R scores higher in 0 categories and MiniMax-M2.1 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.1 leads 58.3 to 38.2.
- Command R is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.1.
- MiniMax-M2.1 accepts more context: 205K tokens versus 128K.

## Snapshot

| | Command R | MiniMax-M2.1 |
|---|---|---|
| Provider | Cohere | MiniMax |
| Noometry Index | 31.4 | 38.9 |
| Rank | 272 | 178 |
| Context | 128K | 205K |
| Input $/M | $0.15 | $0.30 |
| Output $/M | $0.60 | $1.20 |
| Weights | Open | Open |

## Coding

- Command R: 29.3 (#306)
- MiniMax-M2.1: 40.4 (#143)

| Benchmark | Command R | MiniMax-M2.1 |
|---|---|---|
| LMArena Coding | 1169 | 1421 |
| LMArena WebDev | — | 1384 |
| BigCodeBench Instruct | 37.1% | — |
| LiveBench Coding | 17.9% | — |
| BigCodeBench Complete | 45.2% | — |
| ALE-Bench | — | 623.83 |

## Agentic & Tool Use

- Command R: —
- MiniMax-M2.1: 27.9 (#98)

| Benchmark | Command R | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | — | 36.6% |

## Reasoning

- Command R: 13.8 (#331)
- MiniMax-M2.1: 16.6 (#302)

| Benchmark | Command R | MiniMax-M2.1 |
|---|---|---|
| LMArena Hard Prompts | 1164 | 1411 |
| NYT Connections (extended) | — | 11.2% |
| LiveBench Reasoning | 21.9% | — |
| DTBench | 46.4% | — |
| LiveBench Data Analysis | 33.3% | — |
| LMCA | 9.2% | — |
| LiveBench | 27.5% | — |

## Math

- Command R: 28.0 (#246)
- MiniMax-M2.1: 38.3 (#138)

| Benchmark | Command R | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | 1155 | 1397 |
| LiveBench Math | 19.4% | — |

## Knowledge

- Command R: 31.0 (#221)
- MiniMax-M2.1: 38.3 (#147)

| Benchmark | Command R | MiniMax-M2.1 |
|---|---|---|
| LMArena Expert | 1138 | 1431 |
| Vectara Hallucination Rate | — | 11.8% |
| MMLU | 65.2% | — |

## Multilingual

- Command R: 35.7 (#245)
- MiniMax-M2.1: 50.0 (#128)

| Benchmark | Command R | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | 1174 | 1378 |
| LMArena Chinese | 1182 | 1430 |
| LMArena French | 1162 | 1404 |
| LMArena German | 1176 | 1381 |
| LMArena Japanese | 1143 | 1287 |
| LMArena Korean | 1163 | 1298 |
| LMArena Russian | 1174 | 1387 |
| LMArena Spanish | 1151 | 1397 |

## Instruction Following

- Command R: 58.1 (#261)
- MiniMax-M2.1: 73.8 (#112)

| Benchmark | Command R | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | 1167 | 1400 |
| LiveBench Instruction Following | 55.6% | — |

## Long Context

- Command R: 36.3 (#231)
- MiniMax-M2.1: 43.2 (#101)

| Benchmark | Command R | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | 1198 | 1416 |

## Writing & Preference

- Command R: 38.2 (#254)
- MiniMax-M2.1: 58.3 (#120)

| Benchmark | Command R | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | 1187 | 1392 |
| LMArena Creative Writing | 1170 | 1361 |
| LMArena Multi-Turn | 1163 | 1396 |
| LiveBench Language | 16.7% | — |

## FAQ

### Is Command R better than MiniMax-M2.1?

MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 31.4 on the Noometry Index. Command R costs 2.0× less per token, which makes it the better buy when MiniMax-M2.1's lead doesn't matter for your workload.

### Which is cheaper, Command R or MiniMax-M2.1?

Command R is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; MiniMax-M2.1 lists at $0.30 and $1.20.

### Is Command R or MiniMax-M2.1 better for coding?

MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 29.3 in the Noometry coding category.

### Which has the bigger context window?

MiniMax-M2.1 does, with 205K tokens against 128K.

### How many benchmarks do Command R and MiniMax-M2.1 share?

17 benchmarks have published results for both models. Command R has 29 scored results on Noometry and MiniMax-M2.1 has 22.