# Command A vs MiniMax-M3

> MiniMax-M3 is the stronger model overall, scoring 43.8 to 36.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/command-a-vs-minimax-m3
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Command A scores higher in 1 category and MiniMax-M3 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 37.1.
- The biggest single-benchmark swing is LMCA: 10.3% for Command A and 33.7% for MiniMax-M3.
- MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2.50 / $10 for Command A.
- MiniMax-M3 accepts more context: 1M tokens versus 256K.

## Snapshot

| | Command A | MiniMax-M3 |
|---|---|---|
| Provider | Cohere | MiniMax |
| Noometry Index | 36.5 | 43.8 |
| Rank | 215 | 85 |
| Context | 256K | 1M |
| Input $/M | $2.50 | $0.30 |
| Output $/M | $10 | $1.20 |
| Weights | Open | Open |

## Coding

- Command A: 27.2 (#322)
- MiniMax-M3: 41.8 (#118)

| Benchmark | Command A | MiniMax-M3 |
|---|---|---|
| LMArena Coding | 1330 | 1469 |
| FrontierCode | — | 14.7% |
| Aider Polyglot | 12% | — |
| LMArena WebDev | — | 1482 |
| SciCode | — | 47.1% |
| ALE-Bench | — | 640.02 |

## Agentic & Tool Use

- Command A: 35.9 (#40)
- MiniMax-M3: 22.6 (#130)

| Benchmark | Command A | MiniMax-M3 |
|---|---|---|
| APEX-Agents | — | 37.7% |
| Berkeley Function Calling Leaderboard | 57.1% | — |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 2,158 |

## Reasoning

- Command A: 18.3 (#283)
- MiniMax-M3: 30.1 (#87)

| Benchmark | Command A | MiniMax-M3 |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1447 |
| DTBench | 61.3% | 78.9% |
| LMCA | 10.3% | 33.7% |
| SimpleBench | — | 45.8% |
| Kagi LLM Benchmark | 28.8% | — |
| NYT Connections (extended) | — | 65.1% |
| CritPt | — | 3.7% |
| Chess Puzzles | — | 14% |
| Mystery Game Puzzles | — | 8% |
| Surface Evolver Bench | — | 55% |
| Epoch Capabilities Index | — | 146.95 |
| ForecastBench | — | 61.4 |

## Math

- Command A: 36.2 (#171)
- MiniMax-M3: 40.0 (#95)

| Benchmark | Command A | MiniMax-M3 |
|---|---|---|
| LMArena Math | 1300 | 1429 |
| OTIS Mock AIME 2024-2025 | — | 71.1% |
| ProofBench | — | 18% |

## Knowledge

- Command A: 37.1 (#159)
- MiniMax-M3: 58.4 (#35)

| Benchmark | Command A | MiniMax-M3 |
|---|---|---|
| LMArena Expert | 1295 | 1461 |
| GPQA Diamond | — | 90.9% |
| Vectara Hallucination Rate | 9.3% | — |

## Multimodal

- Command A: —
- MiniMax-M3: 40.2 (#51)

| Benchmark | Command A | MiniMax-M3 |
|---|---|---|
| LMArena Vision | — | 1253 |
| LMArena Document | — | 1435 |

## Multilingual

- Command A: 45.3 (#170)
- MiniMax-M3: 53.0 (#75)

| Benchmark | Command A | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | 1313 | 1420 |
| LMArena Chinese | 1327 | 1463 |
| LMArena French | 1351 | 1447 |
| LMArena German | 1341 | 1426 |
| LMArena Japanese | 1285 | 1381 |
| LMArena Korean | 1285 | 1372 |
| LMArena Russian | 1314 | 1428 |
| LMArena Spanish | 1347 | 1432 |

## Instruction Following

- Command A: 69.1 (#177)
- MiniMax-M3: 75.5 (#62)

| Benchmark | Command A | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | 1309 | 1433 |

## Long Context

- Command A: 40.6 (#151)
- MiniMax-M3: 44.2 (#72)

| Benchmark | Command A | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | 1334 | 1445 |

## Writing & Preference

- Command A: 47.6 (#208)
- MiniMax-M3: 62.1 (#83)

| Benchmark | Command A | MiniMax-M3 |
|---|---|---|
| LMArena Text | 1331 | 1433 |
| LMArena Creative Writing | 1319 | 1404 |
| LMArena Multi-Turn | 1339 | 1442 |
| EQ-Bench Creative Writing | 1145 | — |
| EQ-Bench 4 | — | 1150 |

## FAQ

### Is Command A better than MiniMax-M3?

MiniMax-M3 is the stronger model overall, scoring 43.8 to 36.5 on the Noometry Index.

### Which is cheaper, Command A or MiniMax-M3?

MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Command A lists at $2.50 and $10.

### Is Command A or MiniMax-M3 better for coding?

MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 27.2 in the Noometry coding category.

### Which has the bigger context window?

MiniMax-M3 does, with 1M tokens against 256K.

### How many benchmarks do Command A and MiniMax-M3 share?

19 benchmarks have published results for both models. Command A has 24 scored results on Noometry and MiniMax-M3 has 41.