Model comparison
Command R+ vs Mistral 7B
Command R+ is the stronger model overall, scoring 32.4 to 23.0 on the Noometry Index. Mistral 7B costs 18× less per token, which makes it the better buy when Command R+'s lead doesn't matter for your workload.
Last verified . 23 shared benchmarks.
Cohere
Mistral AISummary
- They share 23 benchmarks with published results for both. Command R+ scores higher in 7 categories and Mistral 7B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Command R+ leads 36.4 to 7.4.
- The biggest single-benchmark swing is BigCodeBench Complete: 41.9% for Command R+ and 27.3% for Mistral 7B.
- Mistral 7B is cheaper at $0.25 / $0.25 per million input/output tokens, against $2.50 / $10 for Command R+.
- Command R+ accepts more context: 128K tokens versus 8K.
Side by side
| Command R+ | Mistral 7B | |
|---|---|---|
| Provider | Cohere | Mistral AI |
| Noometry Index | 32.4 | 23.0 |
| Released | 2024-08-30 | 2023-09-27 |
| Weights | Open | Open |
| Context window | 128K | 8K |
| Max output | 4K | 8K |
| Input $ / M tokens | $2.50 | $0.25 |
| Output $ / M tokens | $10 | $0.25 |
| Results tracked | 34 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Command R+ leads
Command R+: 29.1 (#309), Mistral 7B: 26.4 (#326)
| Benchmark | Command R+ | Mistral 7B |
|---|---|---|
| BigCodeBench Instruct | 33.8% | 19.5% |
| LMArena Coding | 1187 | 1082 |
| BigCodeBench Complete | 41.9% | 27.3% |
| HumanEval+ | 56.7% | 36% |
| MBPP+ | 63.5% | 42.1% |
| LiveBench Coding | 19.1% | — |
Reasoning Mistral 7B leads
Command R+: 9.2 (#344), Mistral 7B: 13.1 (#336)
| Benchmark | Command R+ | Mistral 7B |
|---|---|---|
| LMArena Hard Prompts | 1186 | 1067 |
| DTBench | 54.9% | 42.5% |
| Epoch Capabilities Index | 119.34 | 112.21 |
| SimpleBench | 17.4% | — |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | 24.8% | — |
| LiveBench Data Analysis | 38.1% | — |
| LMCA | 5% | — |
| Adversarial NLI | — | 47.1% |
| BIG-Bench Hard | — | 56.1% |
| HellaSwag | — | 81% |
| LiveBench | 31.8% | — |
| PIQA | — | 83% |
| WinoGrande | — | 75.3% |
Math Command R+ leads
Command R+: 28.9 (#242), Mistral 7B: 8.1 (#325)
| Benchmark | Command R+ | Mistral 7B |
|---|---|---|
| LMArena Math | 1188 | 1085 |
| OTIS Mock AIME 2024-2025 | — | 0.3% |
| LiveBench Math | 21.3% | — |
| MATH Level 5 | — | 3.7% |
| GSM8K | — | 54.4% |
Knowledge Command R+ leads
Command R+: 36.4 (#169), Mistral 7B: 7.4 (#311)
| Benchmark | Command R+ | Mistral 7B |
|---|---|---|
| LMArena Expert | 1174 | 1036 |
| MMLU | 69.4% | 62.5% |
| GPQA Diamond | — | 15.2% |
| Vectara Hallucination Rate | 6.9% | — |
| ARC (AI2) Challenge | — | 78.6% |
| BoolQ | — | 87.4% |
| OpenBookQA | — | 79.8% |
| TriviaQA | — | 75.2% |
Multilingual Command R+ leads
Command R+: 38.6 (#227), Mistral 7B: 25.8 (#283)
| Benchmark | Command R+ | Mistral 7B |
|---|---|---|
| LMArena Non-English | 1216 | 1012 |
| LMArena Chinese | 1226 | 1009 |
| LMArena French | 1209 | 1037 |
| LMArena German | 1216 | 987 |
| LMArena Japanese | 1166 | 878 |
| LMArena Russian | 1227 | 1018 |
| LMArena Spanish | 1189 | 1026 |
| LMArena Korean | 1138 | — |
Instruction Following Command R+ leads
Command R+: 60.0 (#254), Mistral 7B: 54.2 (#280)
| Benchmark | Command R+ | Mistral 7B |
|---|---|---|
| LMArena Instruction Following | 1197 | 1060 |
| LiveBench Instruction Following | 57.6% | — |
Long Context Command R+ leads
Command R+: 37.3 (#219), Mistral 7B: 32.2 (#271)
| Benchmark | Command R+ | Mistral 7B |
|---|---|---|
| LMArena Longer Query | 1230 | 1060 |
Writing & Preference Command R+ leads
Command R+: 43.5 (#228), Mistral 7B: 30.7 (#286)
| Benchmark | Command R+ | Mistral 7B |
|---|---|---|
| LMArena Text | 1229 | 1090 |
| LMArena Creative Writing | 1235 | 1068 |
| LMArena Multi-Turn | 1213 | 1062 |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than Mistral 7B?
Command R+ is the stronger model overall, scoring 32.4 to 23.0 on the Noometry Index. Mistral 7B costs 18× less per token, which makes it the better buy when Command R+'s lead doesn't matter for your workload.
Which is cheaper, Command R+ or Mistral 7B?
Mistral 7B is cheaper. It lists at $0.25 per million input tokens and $0.25 per million output tokens; Command R+ lists at $2.50 and $10.
Is Command R+ or Mistral 7B better for coding?
Command R+ scores higher on coding benchmarks: 29.1 versus 26.4 in the Noometry coding category.
Which has the bigger context window?
Command R+ does, with 128K tokens against 8K.
How many benchmarks do Command R+ and Mistral 7B share?
23 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Mistral 7B has 37.