Model comparison
Command R+ vs MiniMax-M2
MiniMax-M2 is the stronger model overall, scoring 37.4 to 32.4 on the Noometry Index.
Last verified . 15 shared benchmarks.
Cohere
MiniMaxSummary
- They share 15 benchmarks with published results for both. Command R+ scores higher in 0 categories and MiniMax-M2 in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where MiniMax-M2 leads 70.2 to 60.0.
- MiniMax-M2 is cheaper at $0.30 / $1.20 per million input/output tokens, against $2.50 / $10 for Command R+.
- MiniMax-M2 accepts more context: 205K tokens versus 128K.
Side by side
| Command R+ | MiniMax-M2 | |
|---|---|---|
| Provider | Cohere | MiniMax |
| Noometry Index | 32.4 | 37.4 |
| Released | 2024-08-30 | 2025-10-27 |
| Weights | Open | Open |
| Context window | 128K | 205K |
| Max output | 4K | 131K |
| Input $ / M tokens | $2.50 | $0.30 |
| Output $ / M tokens | $10 | $1.20 |
| Results tracked | 34 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2 leads
Command R+: 29.1 (#309), MiniMax-M2: 39.3 (#159)
| Benchmark | Command R+ | MiniMax-M2 |
|---|---|---|
| LMArena Coding | 1187 | 1370 |
| SWE-bench Verified (bash only) | — | 61% |
| LMArena WebDev | — | 1297 |
| BigCodeBench Instruct | 33.8% | — |
| LiveBench Coding | 19.1% | — |
| BigCodeBench Complete | 41.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |
Agentic & Tool Use Not comparable
Command R+: —, MiniMax-M2: 25.1 (#109)
| Benchmark | Command R+ | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| Vending-Bench 2 | — | 160.6 |
Reasoning MiniMax-M2 leads
Command R+: 9.2 (#344), MiniMax-M2: 19.4 (#258)
| Benchmark | Command R+ | MiniMax-M2 |
|---|---|---|
| LMArena Hard Prompts | 1186 | 1357 |
| SimpleBench | 17.4% | — |
| Kagi LLM Benchmark | — | 57.8% |
| NYT Connections (extended) | — | 14.8% |
| LiveBench Reasoning | 24.8% | — |
| DTBench | 54.9% | — |
| LiveBench Data Analysis | 38.1% | — |
| LMCA | 5% | — |
| Epoch Capabilities Index | 119.34 | — |
| LiveBench | 31.8% | — |
Math MiniMax-M2 leads
Command R+: 28.9 (#242), MiniMax-M2: 37.3 (#160)
| Benchmark | Command R+ | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1188 | 1352 |
| LiveBench Math | 21.3% | — |
Knowledge Too close to call
Command R+: 36.4 (#169), MiniMax-M2: 37.0 (#163)
| Benchmark | Command R+ | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1174 | 1337 |
| Vectara Hallucination Rate | 6.9% | — |
| MMLU | 69.4% | — |
Multilingual MiniMax-M2 leads
Command R+: 38.6 (#227), MiniMax-M2: 45.3 (#171)
| Benchmark | Command R+ | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1216 | 1313 |
| LMArena Chinese | 1226 | 1366 |
| LMArena French | 1209 | 1335 |
| LMArena German | 1216 | 1355 |
| LMArena Russian | 1227 | 1331 |
| LMArena Spanish | 1189 | 1326 |
| LMArena Japanese | 1166 | — |
| LMArena Korean | 1138 | — |
Instruction Following MiniMax-M2 leads
Command R+: 60.0 (#254), MiniMax-M2: 70.2 (#166)
| Benchmark | Command R+ | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1197 | 1328 |
| LiveBench Instruction Following | 57.6% | — |
Long Context MiniMax-M2 leads
Command R+: 37.3 (#219), MiniMax-M2: 40.5 (#153)
| Benchmark | Command R+ | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1230 | 1331 |
Writing & Preference MiniMax-M2 leads
Command R+: 43.5 (#228), MiniMax-M2: 53.0 (#162)
| Benchmark | Command R+ | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1229 | 1340 |
| LMArena Creative Writing | 1235 | 1286 |
| LMArena Multi-Turn | 1213 | 1361 |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than MiniMax-M2?
MiniMax-M2 is the stronger model overall, scoring 37.4 to 32.4 on the Noometry Index.
Which is cheaper, Command R+ or MiniMax-M2?
MiniMax-M2 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Command R+ lists at $2.50 and $10.
Is Command R+ or MiniMax-M2 better for coding?
MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 29.1 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2 does, with 205K tokens against 128K.
How many benchmarks do Command R+ and MiniMax-M2 share?
15 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and MiniMax-M2 has 21.