Model comparison
Command A vs MiMo-V2-Pro
MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 36.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
CohereSummary
- They share 17 benchmarks with published results for both. Command A scores higher in 0 categories and MiMo-V2-Pro in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiMo-V2-Pro leads 43.8 to 27.2.
- MiMo-V2-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $2.50 / $10 for Command A.
- MiMo-V2-Pro accepts more context: 1.05M tokens versus 256K.
- Command A has downloadable open weights; the other is API-only.
Side by side
| Command A | MiMo-V2-Pro | |
|---|---|---|
| Provider | Cohere | Xiaomi |
| Noometry Index | 36.5 | 43.0 |
| Released | 2025-03-13 | 2026-03-18 |
| Weights | Open | Proprietary |
| Context window | 256K | 1.05M |
| Max output | 8K | 131K |
| Input $ / M tokens | $2.50 | $0.43 |
| Output $ / M tokens | $10 | $0.87 |
| Results tracked | 24 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2-Pro leads
Command A: 27.2 (#322), MiMo-V2-Pro: 43.8 (#83)
| Benchmark | Command A | MiMo-V2-Pro |
|---|---|---|
| LMArena Coding | 1330 | 1476 |
| Aider Polyglot | 12% | — |
| LMArena WebDev | — | 1433 |
| ALE-Bench | — | 785.17 |
Agentic & Tool Use Not comparable
Command A: 35.9 (#40), MiMo-V2-Pro: —
| Benchmark | Command A | MiMo-V2-Pro |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
Reasoning MiMo-V2-Pro leads
Command A: 18.3 (#283), MiMo-V2-Pro: 22.1 (#206)
| Benchmark | Command A | MiMo-V2-Pro |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1457 |
| Kagi LLM Benchmark | 28.8% | — |
| NYT Connections (extended) | — | 25.8% |
| Thematic Generalization | — | 45.9% |
| DTBench | 61.3% | — |
| LMCA | 10.3% | — |
Math MiMo-V2-Pro leads
Command A: 36.2 (#171), MiMo-V2-Pro: 39.5 (#102)
| Benchmark | Command A | MiMo-V2-Pro |
|---|---|---|
| LMArena Math | 1300 | 1447 |
Knowledge MiMo-V2-Pro leads
Command A: 37.1 (#159), MiMo-V2-Pro: 41.4 (#111)
| Benchmark | Command A | MiMo-V2-Pro |
|---|---|---|
| LMArena Expert | 1295 | 1478 |
| Vectara Hallucination Rate | 9.3% | — |
Multilingual MiMo-V2-Pro leads
Command A: 45.3 (#170), MiMo-V2-Pro: 52.7 (#81)
| Benchmark | Command A | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | 1313 | 1416 |
| LMArena Chinese | 1327 | 1456 |
| LMArena French | 1351 | 1469 |
| LMArena German | 1341 | 1417 |
| LMArena Japanese | 1285 | 1366 |
| LMArena Korean | 1285 | 1400 |
| LMArena Russian | 1314 | 1427 |
| LMArena Spanish | 1347 | 1457 |
Instruction Following MiMo-V2-Pro leads
Command A: 69.1 (#177), MiMo-V2-Pro: 76.0 (#49)
| Benchmark | Command A | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | 1309 | 1445 |
Long Context Too close to call
Command A: 40.6 (#151), MiMo-V2-Pro: 41.5 (#138)
| Benchmark | Command A | MiMo-V2-Pro |
|---|---|---|
| LMArena Longer Query | 1334 | 1455 |
| CL-bench | — | 15.7% |
| CL-bench Life | — | 6.9% |
Writing & Preference MiMo-V2-Pro leads
Command A: 47.6 (#208), MiMo-V2-Pro: 62.8 (#70)
| Benchmark | Command A | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | 1331 | 1436 |
| LMArena Creative Writing | 1319 | 1415 |
| LMArena Multi-Turn | 1339 | 1456 |
| EQ-Bench Creative Writing | 1145 | — |
Frequently asked questions
Is Command A better than MiMo-V2-Pro?
MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 36.5 on the Noometry Index.
Which is cheaper, Command A or MiMo-V2-Pro?
MiMo-V2-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Command A lists at $2.50 and $10.
Is Command A or MiMo-V2-Pro better for coding?
MiMo-V2-Pro scores higher on coding benchmarks: 43.8 versus 27.2 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2-Pro does, with 1.05M tokens against 256K.
How many benchmarks do Command A and MiMo-V2-Pro share?
17 benchmarks have published results for both models. Command A has 24 scored results on Noometry and MiMo-V2-Pro has 23.