Model comparison
Command A vs MiniMax-M2.5
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 36.5 on the Noometry Index.
Last verified . 20 shared benchmarks.
Cohere
MiniMaxSummary
- They share 20 benchmarks with published results for both. Command A scores higher in 4 categories and MiniMax-M2.5 in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M2.5 leads 48.1 to 27.2.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 28.8% for Command A and 55.2% for MiniMax-M2.5.
- MiniMax-M2.5 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2.50 / $10 for Command A.
- Command A accepts more context: 256K tokens versus 205K.
Side by side
| Command A | MiniMax-M2.5 | |
|---|---|---|
| Provider | Cohere | MiniMax |
| Noometry Index | 36.5 | 38.3 |
| Released | 2025-03-13 | 2026-02-12 |
| Weights | Open | Open |
| Context window | 256K | 205K |
| Max output | 8K | 131K |
| Input $ / M tokens | $2.50 | $0.30 |
| Output $ / M tokens | $10 | $1.20 |
| Results tracked | 24 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.5 leads
Command A: 27.2 (#322), MiniMax-M2.5: 48.1 (#58)
| Benchmark | Command A | MiniMax-M2.5 |
|---|---|---|
| LMArena Coding | 1330 | 1381 |
| SWE-bench Verified (bash only) | — | 75.8% |
| Aider Polyglot | 12% | — |
| LMArena WebDev | — | 1387 |
| SWE-bench Multilingual | — | 68.3% |
| ALE-Bench | — | 618.17 |
Agentic & Tool Use Command A leads
Command A: 35.9 (#40), MiniMax-M2.5: 30.4 (#77)
| Benchmark | Command A | MiniMax-M2.5 |
|---|---|---|
| Terminal-Bench | — | 42.7% |
| Berkeley Function Calling Leaderboard | 57.1% | — |
| Vending-Bench 2 | — | -23.16 |
Reasoning Too close to call
Command A: 18.3 (#283), MiniMax-M2.5: 17.5 (#292)
| Benchmark | Command A | MiniMax-M2.5 |
|---|---|---|
| Kagi LLM Benchmark | 28.8% | 55.2% |
| LMArena Hard Prompts | 1326 | 1372 |
| ARC-AGI-2 | — | 4.9% |
| NYT Connections (extended) | — | 16.8% |
| ARC-AGI-1 | — | 63.7% |
| DTBench | 61.3% | — |
| LMCA | 10.3% | — |
| Epoch Capabilities Index | — | 146.68 |
Math Command A leads
Command A: 36.2 (#171), MiniMax-M2.5: 26.9 (#253)
| Benchmark | Command A | MiniMax-M2.5 |
|---|---|---|
| LMArena Math | 1300 | 1378 |
| ProofBench | — | 4% |
Knowledge MiniMax-M2.5 leads
Command A: 37.1 (#159), MiniMax-M2.5: 39.2 (#135)
| Benchmark | Command A | MiniMax-M2.5 |
|---|---|---|
| Vectara Hallucination Rate | 9.3% | 9.1% |
| LMArena Expert | 1295 | 1379 |
Multilingual MiniMax-M2.5 leads
Command A: 45.3 (#170), MiniMax-M2.5: 47.1 (#152)
| Benchmark | Command A | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1313 | 1338 |
| LMArena Chinese | 1327 | 1393 |
| LMArena French | 1351 | 1362 |
| LMArena German | 1341 | 1362 |
| LMArena Japanese | 1285 | 1171 |
| LMArena Korean | 1285 | 1232 |
| LMArena Russian | 1314 | 1358 |
| LMArena Spanish | 1347 | 1354 |
Instruction Following MiniMax-M2.5 leads
Command A: 69.1 (#177), MiniMax-M2.5: 71.5 (#148)
| Benchmark | Command A | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1309 | 1353 |
Long Context Command A leads
Command A: 40.6 (#151), MiniMax-M2.5: 37.5 (#216)
| Benchmark | Command A | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 1334 | 1366 |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |
Writing & Preference MiniMax-M2.5 leads
Command A: 47.6 (#208), MiniMax-M2.5: 53.9 (#153)
| Benchmark | Command A | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1331 | 1359 |
| LMArena Creative Writing | 1319 | 1331 |
| EQ-Bench Creative Writing | 1145 | 1361 |
| LMArena Multi-Turn | 1339 | 1364 |
Frequently asked questions
Is Command A better than MiniMax-M2.5?
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 36.5 on the Noometry Index.
Which is cheaper, Command A or MiniMax-M2.5?
MiniMax-M2.5 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-M2.5 better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 27.2 in the Noometry coding category.
Which has the bigger context window?
Command A does, with 256K tokens against 205K.
How many benchmarks do Command A and MiniMax-M2.5 share?
20 benchmarks have published results for both models. Command A has 24 scored results on Noometry and MiniMax-M2.5 has 33.