Model comparison
Command R+ vs Llama 13b
Command R+ is the stronger model overall, scoring 32.4 to 24.4 on the Noometry Index.
Last verified . 10 shared benchmarks.
Cohere
MetaSummary
- They share 10 benchmarks with published results for both. Command R+ scores higher in 5 categories and Llama 13b in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Command R+ leads 43.5 to 13.8.
Side by side
| Command R+ | Llama 13b | |
|---|---|---|
| Provider | Cohere | Meta |
| Noometry Index | 32.4 | 24.4 |
| Released | 2024-08-30 | 2023-02-24 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $2.50 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 34 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Command R+ leads
Command R+: 29.1 (#309), Llama 13b: 21.4 (#337)
| Benchmark | Command R+ | Llama 13b |
|---|---|---|
| LMArena Coding | 1187 | 683 |
| BigCodeBench Instruct | 33.8% | — |
| LiveBench Coding | 19.1% | — |
| BigCodeBench Complete | 41.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |
Reasoning Llama 13b leads
Command R+: 9.2 (#344), Llama 13b: 14.0 (#329)
| Benchmark | Command R+ | Llama 13b |
|---|---|---|
| LMArena Hard Prompts | 1186 | 728 |
| Epoch Capabilities Index | 119.34 | 100.58 |
| SimpleBench | 17.4% | — |
| LiveBench Reasoning | 24.8% | — |
| DTBench | 54.9% | — |
| LiveBench Data Analysis | 38.1% | — |
| LMCA | 5% | — |
| BIG-Bench Hard | — | 37.9% |
| HellaSwag | — | 79.2% |
| LAMBADA | — | 75.2% |
| LiveBench | 31.8% | — |
| PIQA | — | 80.1% |
| WinoGrande | — | 73% |
Math Command R+ leads
Command R+: 28.9 (#242), Llama 13b: 26.7 (#256)
| Benchmark | Command R+ | Llama 13b |
|---|---|---|
| LMArena Math | 1188 | 838 |
| LiveBench Math | 21.3% | — |
| GSM8K | — | 20.6% |
Knowledge Not comparable
Command R+: 36.4 (#169), Llama 13b: —
| Benchmark | Command R+ | Llama 13b |
|---|---|---|
| MMLU | 69.4% | 47.7% |
| Vectara Hallucination Rate | 6.9% | — |
| LMArena Expert | 1174 | — |
| ARC (AI2) Challenge | — | 52.7% |
| BoolQ | — | 78.7% |
| OpenBookQA | — | 56.4% |
| TriviaQA | — | 77.9% |
Multimodal Not comparable
Command R+: —, Llama 13b: —
| Benchmark | Command R+ | Llama 13b |
|---|---|---|
| ScienceQA | — | 43.3% |
Multilingual Command R+ leads
Command R+: 38.6 (#227), Llama 13b: 16.6 (#297)
| Benchmark | Command R+ | Llama 13b |
|---|---|---|
| LMArena Non-English | 1216 | 819 |
| LMArena Chinese | 1226 | — |
| LMArena French | 1209 | — |
| LMArena German | 1216 | — |
| LMArena Japanese | 1166 | — |
| LMArena Korean | 1138 | — |
| LMArena Russian | 1227 | — |
| LMArena Spanish | 1189 | — |
Instruction Following Command R+ leads
Command R+: 60.0 (#254), Llama 13b: 36.7 (#305)
| Benchmark | Command R+ | Llama 13b |
|---|---|---|
| LMArena Instruction Following | 1197 | 781 |
| LiveBench Instruction Following | 57.6% | — |
Long Context Not comparable
Command R+: 37.3 (#219), Llama 13b: —
| Benchmark | Command R+ | Llama 13b |
|---|---|---|
| LMArena Longer Query | 1230 | — |
Writing & Preference Command R+ leads
Command R+: 43.5 (#228), Llama 13b: 13.8 (#312)
| Benchmark | Command R+ | Llama 13b |
|---|---|---|
| LMArena Text | 1229 | 834 |
| LMArena Creative Writing | 1235 | 794 |
| LMArena Multi-Turn | 1213 | 753 |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than Llama 13b?
Command R+ is the stronger model overall, scoring 32.4 to 24.4 on the Noometry Index.
Is Command R+ or Llama 13b better for coding?
Command R+ scores higher on coding benchmarks: 29.1 versus 21.4 in the Noometry coding category.
How many benchmarks do Command R+ and Llama 13b share?
10 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Llama 13b has 21.