Model comparison
Command A vs Command R+
Command A is the stronger model overall, scoring 36.5 to 32.4 on the Noometry Index.
Last verified . 20 shared benchmarks.
CohereSummary
- They share 20 benchmarks with published results for both. Command A scores higher in 7 categories and Command R+ in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Command A leads 69.1 to 60.0.
- The biggest single-benchmark swing is DTBench: 61.3% for Command A and 54.9% for Command R+.
- Both cost about the same: $2.50 input and $10 output per million tokens.
- Command A accepts more context: 256K tokens versus 128K.
Side by side
| Command A | Command R+ | |
|---|---|---|
| Provider | Cohere | Cohere |
| Noometry Index | 36.5 | 32.4 |
| Released | 2025-03-13 | 2024-08-30 |
| Weights | Open | Open |
| Context window | 256K | 128K |
| Max output | 8K | 4K |
| Input $ / M tokens | $2.50 | $2.50 |
| Output $ / M tokens | $10 | $10 |
| Results tracked | 24 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Command R+ leads
Command A: 27.2 (#322), Command R+: 29.1 (#309)
| Benchmark | Command A | Command R+ |
|---|---|---|
| LMArena Coding | 1330 | 1187 |
| Aider Polyglot | 12% | — |
| BigCodeBench Instruct | — | 33.8% |
| LiveBench Coding | — | 19.1% |
| BigCodeBench Complete | — | 41.9% |
| HumanEval+ | — | 56.7% |
| MBPP+ | — | 63.5% |
Agentic & Tool Use Not comparable
Command A: 35.9 (#40), Command R+: —
| Benchmark | Command A | Command R+ |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
Reasoning Command A leads
Command A: 18.3 (#283), Command R+: 9.2 (#344)
| Benchmark | Command A | Command R+ |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1186 |
| DTBench | 61.3% | 54.9% |
| LMCA | 10.3% | 5% |
| SimpleBench | — | 17.4% |
| Kagi LLM Benchmark | 28.8% | — |
| LiveBench Reasoning | — | 24.8% |
| LiveBench Data Analysis | — | 38.1% |
| Epoch Capabilities Index | — | 119.34 |
| LiveBench | — | 31.8% |
Math Command A leads
Command A: 36.2 (#171), Command R+: 28.9 (#242)
| Benchmark | Command A | Command R+ |
|---|---|---|
| LMArena Math | 1300 | 1188 |
| LiveBench Math | — | 21.3% |
Knowledge Too close to call
Command A: 37.1 (#159), Command R+: 36.4 (#169)
| Benchmark | Command A | Command R+ |
|---|---|---|
| Vectara Hallucination Rate | 9.3% | 6.9% |
| LMArena Expert | 1295 | 1174 |
| MMLU | — | 69.4% |
Multilingual Command A leads
Command A: 45.3 (#170), Command R+: 38.6 (#227)
| Benchmark | Command A | Command R+ |
|---|---|---|
| LMArena Non-English | 1313 | 1216 |
| LMArena Chinese | 1327 | 1226 |
| LMArena French | 1351 | 1209 |
| LMArena German | 1341 | 1216 |
| LMArena Japanese | 1285 | 1166 |
| LMArena Korean | 1285 | 1138 |
| LMArena Russian | 1314 | 1227 |
| LMArena Spanish | 1347 | 1189 |
Instruction Following Command A leads
Command A: 69.1 (#177), Command R+: 60.0 (#254)
| Benchmark | Command A | Command R+ |
|---|---|---|
| LMArena Instruction Following | 1309 | 1197 |
| LiveBench Instruction Following | — | 57.6% |
Long Context Command A leads
Command A: 40.6 (#151), Command R+: 37.3 (#219)
| Benchmark | Command A | Command R+ |
|---|---|---|
| LMArena Longer Query | 1334 | 1230 |
Writing & Preference Command A leads
Command A: 47.6 (#208), Command R+: 43.5 (#228)
| Benchmark | Command A | Command R+ |
|---|---|---|
| LMArena Text | 1331 | 1229 |
| LMArena Creative Writing | 1319 | 1235 |
| LMArena Multi-Turn | 1339 | 1213 |
| EQ-Bench Creative Writing | 1145 | — |
| LiveBench Language | — | 29.7% |
Frequently asked questions
Is Command A better than Command R+?
Command A is the stronger model overall, scoring 36.5 to 32.4 on the Noometry Index.
Which is cheaper, Command A or Command R+?
Command R+ is cheaper. It lists at $2.50 per million input tokens and $10 per million output tokens; Command A lists at $2.50 and $10.
Is Command A or Command R+ better for coding?
Command R+ scores higher on coding benchmarks: 29.1 versus 27.2 in the Noometry coding category.
Which has the bigger context window?
Command A does, with 256K tokens against 128K.
How many benchmarks do Command A and Command R+ share?
20 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Command R+ has 34.