Model comparison
Command R vs MiniMax-M2.5
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 31.4 on the Noometry Index. Command R costs 2.0× less per token, which makes it the better buy when MiniMax-M2.5's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Cohere
MiniMaxSummary
- They share 17 benchmarks with published results for both. Command R scores higher in 1 category and MiniMax-M2.5 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M2.5 leads 48.1 to 29.3.
- Command R is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.5.
- MiniMax-M2.5 accepts more context: 205K tokens versus 128K.
Side by side
| Command R | MiniMax-M2.5 | |
|---|---|---|
| Provider | Cohere | MiniMax |
| Noometry Index | 31.4 | 38.3 |
| Released | 2024-08-30 | 2026-02-12 |
| Weights | Open | Open |
| Context window | 128K | 205K |
| Max output | 4K | 131K |
| Input $ / M tokens | $0.15 | $0.30 |
| Output $ / M tokens | $0.60 | $1.20 |
| Results tracked | 29 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.5 leads
Command R: 29.3 (#306), MiniMax-M2.5: 48.1 (#58)
| Benchmark | Command R | MiniMax-M2.5 |
|---|---|---|
| LMArena Coding | 1169 | 1381 |
| SWE-bench Verified (bash only) | — | 75.8% |
| LMArena WebDev | — | 1387 |
| SWE-bench Multilingual | — | 68.3% |
| BigCodeBench Instruct | 37.1% | — |
| LiveBench Coding | 17.9% | — |
| BigCodeBench Complete | 45.2% | — |
| ALE-Bench | — | 618.17 |
Agentic & Tool Use Not comparable
Command R: —, MiniMax-M2.5: 30.4 (#77)
| Benchmark | Command R | MiniMax-M2.5 |
|---|---|---|
| Terminal-Bench | — | 42.7% |
| Vending-Bench 2 | — | -23.16 |
Reasoning MiniMax-M2.5 leads
Command R: 13.8 (#331), MiniMax-M2.5: 17.5 (#292)
| Benchmark | Command R | MiniMax-M2.5 |
|---|---|---|
| LMArena Hard Prompts | 1164 | 1372 |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 55.2% |
| NYT Connections (extended) | — | 16.8% |
| ARC-AGI-1 | — | 63.7% |
| LiveBench Reasoning | 21.9% | — |
| DTBench | 46.4% | — |
| LiveBench Data Analysis | 33.3% | — |
| LMCA | 9.2% | — |
| Epoch Capabilities Index | — | 146.68 |
| LiveBench | 27.5% | — |
Math Command R leads
Command R: 28.0 (#246), MiniMax-M2.5: 26.9 (#253)
| Benchmark | Command R | MiniMax-M2.5 |
|---|---|---|
| LMArena Math | 1155 | 1378 |
| ProofBench | — | 4% |
| LiveBench Math | 19.4% | — |
Knowledge MiniMax-M2.5 leads
Command R: 31.0 (#221), MiniMax-M2.5: 39.2 (#135)
| Benchmark | Command R | MiniMax-M2.5 |
|---|---|---|
| LMArena Expert | 1138 | 1379 |
| Vectara Hallucination Rate | — | 9.1% |
| MMLU | 65.2% | — |
Multilingual MiniMax-M2.5 leads
Command R: 35.7 (#245), MiniMax-M2.5: 47.1 (#152)
| Benchmark | Command R | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1174 | 1338 |
| LMArena Chinese | 1182 | 1393 |
| LMArena French | 1162 | 1362 |
| LMArena German | 1176 | 1362 |
| LMArena Japanese | 1143 | 1171 |
| LMArena Korean | 1163 | 1232 |
| LMArena Russian | 1174 | 1358 |
| LMArena Spanish | 1151 | 1354 |
Instruction Following MiniMax-M2.5 leads
Command R: 58.1 (#261), MiniMax-M2.5: 71.5 (#148)
| Benchmark | Command R | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1167 | 1353 |
| LiveBench Instruction Following | 55.6% | — |
Long Context MiniMax-M2.5 leads
Command R: 36.3 (#231), MiniMax-M2.5: 37.5 (#216)
| Benchmark | Command R | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 1198 | 1366 |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |
Writing & Preference MiniMax-M2.5 leads
Command R: 38.2 (#254), MiniMax-M2.5: 53.9 (#153)
| Benchmark | Command R | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1187 | 1359 |
| LMArena Creative Writing | 1170 | 1331 |
| LMArena Multi-Turn | 1163 | 1364 |
| EQ-Bench Creative Writing | — | 1361 |
| LiveBench Language | 16.7% | — |
Frequently asked questions
Is Command R better than MiniMax-M2.5?
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 31.4 on the Noometry Index. Command R costs 2.0× less per token, which makes it the better buy when MiniMax-M2.5's lead doesn't matter for your workload.
Which is cheaper, Command R or MiniMax-M2.5?
Command R is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; MiniMax-M2.5 lists at $0.30 and $1.20.
Is Command R or MiniMax-M2.5 better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 29.3 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2.5 does, with 205K tokens against 128K.
How many benchmarks do Command R and MiniMax-M2.5 share?
17 benchmarks have published results for both models. Command R has 29 scored results on Noometry and MiniMax-M2.5 has 33.