Model comparison
Command R+ vs Mixtral 8x7B
Command R+ is the stronger model overall, scoring 32.4 to 27.1 on the Noometry Index. Mixtral 8x7B costs 6.3× less per token, which makes it the better buy when Command R+'s lead doesn't matter for your workload.
Last verified . 22 shared benchmarks.
Cohere
Mistral AISummary
- They share 22 benchmarks with published results for both. Command R+ scores higher in 6 categories and Mixtral 8x7B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Command R+ leads 36.4 to 11.0.
- The biggest single-benchmark swing is DTBench: 54.9% for Command R+ and 49.6% for Mixtral 8x7B.
- Mixtral 8x7B is cheaper at $0.70 / $0.70 per million input/output tokens, against $2.50 / $10 for Command R+.
- Command R+ accepts more context: 128K tokens versus 32K.
Side by side
| Command R+ | Mixtral 8x7B | |
|---|---|---|
| Provider | Cohere | Mistral AI |
| Noometry Index | 32.4 | 27.1 |
| Released | 2024-08-30 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 128K | 32K |
| Max output | 4K | 32K |
| Input $ / M tokens | $2.50 | $0.70 |
| Output $ / M tokens | $10 | $0.70 |
| Results tracked | 34 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mixtral 8x7B leads
Command R+: 29.1 (#309), Mixtral 8x7B: 32.8 (#269)
| Benchmark | Command R+ | Mixtral 8x7B |
|---|---|---|
| LMArena Coding | 1187 | 1126 |
| HumanEval+ | 56.7% | 39.6% |
| MBPP+ | 63.5% | 49.7% |
| BigCodeBench Instruct | 33.8% | — |
| LiveBench Coding | 19.1% | — |
| BigCodeBench Complete | 41.9% | — |
Reasoning Mixtral 8x7B leads
Command R+: 9.2 (#344), Mixtral 8x7B: 18.2 (#285)
| Benchmark | Command R+ | Mixtral 8x7B |
|---|---|---|
| LMArena Hard Prompts | 1186 | 1115 |
| DTBench | 54.9% | 49.6% |
| Epoch Capabilities Index | 119.34 | 118.47 |
| SimpleBench | 17.4% | — |
| LiveBench Reasoning | 24.8% | — |
| LiveBench Data Analysis | 38.1% | — |
| LMCA | 5% | — |
| Adversarial NLI | — | 55.2% |
| ForecastBench | — | 56.3 |
| HellaSwag | — | 86.7% |
| LiveBench | 31.8% | — |
| PIQA | — | 83.6% |
| WinoGrande | — | 77.2% |
Math Command R+ leads
Command R+: 28.9 (#242), Mixtral 8x7B: 18.8 (#289)
| Benchmark | Command R+ | Mixtral 8x7B |
|---|---|---|
| LMArena Math | 1188 | 1147 |
| Omni-MATH | — | 10.5% |
| LiveBench Math | 21.3% | — |
| MATH Level 5 | — | 10% |
| GSM8K | — | 74.4% |
Knowledge Command R+ leads
Command R+: 36.4 (#169), Mixtral 8x7B: 11.0 (#301)
| Benchmark | Command R+ | Mixtral 8x7B |
|---|---|---|
| LMArena Expert | 1174 | 1088 |
| MMLU | 69.4% | 70.6% |
| GPQA Diamond | — | 30.6% |
| MMLU-Pro | — | 33.5% |
| Vectara Hallucination Rate | 6.9% | — |
| GPQA (HELM) | — | 29.6% |
| ARC (AI2) Challenge | — | 87.3% |
| OpenBookQA | — | 85.8% |
| TriviaQA | — | 82.2% |
Multilingual Command R+ leads
Command R+: 38.6 (#227), Mixtral 8x7B: 29.6 (#266)
| Benchmark | Command R+ | Mixtral 8x7B |
|---|---|---|
| LMArena Non-English | 1216 | 1077 |
| LMArena Chinese | 1226 | 1055 |
| LMArena French | 1209 | 1166 |
| LMArena German | 1216 | 1114 |
| LMArena Japanese | 1166 | 931 |
| LMArena Korean | 1138 | 968 |
| LMArena Russian | 1227 | 1090 |
| LMArena Spanish | 1189 | 1111 |
Instruction Following Command R+ leads
Command R+: 60.0 (#254), Mixtral 8x7B: 51.0 (#297)
| Benchmark | Command R+ | Mixtral 8x7B |
|---|---|---|
| LMArena Instruction Following | 1197 | 1109 |
| LiveBench Instruction Following | 57.6% | — |
| IFEval | — | 57.5% |
Long Context Command R+ leads
Command R+: 37.3 (#219), Mixtral 8x7B: 33.4 (#260)
| Benchmark | Command R+ | Mixtral 8x7B |
|---|---|---|
| LMArena Longer Query | 1230 | 1103 |
Writing & Preference Command R+ leads
Command R+: 43.5 (#228), Mixtral 8x7B: 34.2 (#270)
| Benchmark | Command R+ | Mixtral 8x7B |
|---|---|---|
| LMArena Text | 1229 | 1132 |
| LMArena Creative Writing | 1235 | 1109 |
| LMArena Multi-Turn | 1213 | 1115 |
| WildBench | — | 67.3% |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than Mixtral 8x7B?
Command R+ is the stronger model overall, scoring 32.4 to 27.1 on the Noometry Index. Mixtral 8x7B costs 6.3× 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 Mixtral 8x7B?
Mixtral 8x7B is cheaper. It lists at $0.70 per million input tokens and $0.70 per million output tokens; Command R+ lists at $2.50 and $10.
Is Command R+ or Mixtral 8x7B better for coding?
Mixtral 8x7B scores higher on coding benchmarks: 32.8 versus 29.1 in the Noometry coding category.
Which has the bigger context window?
Command R+ does, with 128K tokens against 32K.
How many benchmarks do Command R+ and Mixtral 8x7B share?
22 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Mixtral 8x7B has 38.