Model comparison
Command R vs Llama 3-8B
Command R is the stronger model overall, scoring 31.4 to 25.5 on the Noometry Index.
Last verified . 21 shared benchmarks.
Cohere
MetaSummary
- They share 21 benchmarks with published results for both. Command R scores higher in 5 categories and Llama 3-8B in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Command R leads 31.0 to 7.8.
- The biggest single-benchmark swing is BigCodeBench Complete: 45.2% for Command R and 36.9% for Llama 3-8B.
Side by side
| Command R | Llama 3-8B | |
|---|---|---|
| Provider | Cohere | Meta |
| Noometry Index | 31.4 | 25.5 |
| Released | 2024-08-30 | 2024-04-18 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 29 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-8B leads
Command R: 29.3 (#306), Llama 3-8B: 31.0 (#289)
| Benchmark | Command R | Llama 3-8B |
|---|---|---|
| BigCodeBench Instruct | 37.1% | 31.9% |
| LMArena Coding | 1169 | 1152 |
| BigCodeBench Complete | 45.2% | 36.9% |
| LiveBench Coding | 17.9% | — |
| HumanEval+ | — | 56.7% |
| MBPP+ | — | 54.8% |
Reasoning Too close to call
Command R: 13.8 (#331), Llama 3-8B: 14.3 (#326)
| Benchmark | Command R | Llama 3-8B |
|---|---|---|
| LMArena Hard Prompts | 1164 | 1133 |
| DTBench | 46.4% | 43.9% |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | 21.9% | — |
| LiveBench Data Analysis | 33.3% | — |
| LMCA | 9.2% | — |
| Adversarial NLI | — | 57.3% |
| Epoch Capabilities Index | — | 116.45 |
| ForecastBench | — | 58.6 |
| LiveBench | 27.5% | — |
| WinoGrande | — | 75.7% |
Math Command R leads
Command R: 28.0 (#246), Llama 3-8B: 8.8 (#323)
| Benchmark | Command R | Llama 3-8B |
|---|---|---|
| LMArena Math | 1155 | 1151 |
| OTIS Mock AIME 2024-2025 | — | 1.9% |
| LiveBench Math | 19.4% | — |
| MATH Level 5 | — | 6.1% |
Knowledge Command R leads
Command R: 31.0 (#221), Llama 3-8B: 7.8 (#308)
| Benchmark | Command R | Llama 3-8B |
|---|---|---|
| LMArena Expert | 1138 | 1113 |
| MMLU | 65.2% | 68.8% |
| GPQA Diamond | — | 26.1% |
| ARC (AI2) Challenge | — | 82.8% |
| OpenBookQA | — | 82.6% |
| TriviaQA | — | 67.7% |
Multilingual Command R leads
Command R: 35.7 (#245), Llama 3-8B: 30.8 (#261)
| Benchmark | Command R | Llama 3-8B |
|---|---|---|
| LMArena Non-English | 1174 | 1098 |
| LMArena Chinese | 1182 | 1076 |
| LMArena French | 1162 | 1159 |
| LMArena German | 1176 | 1104 |
| LMArena Japanese | 1143 | 967 |
| LMArena Korean | 1163 | 1004 |
| LMArena Russian | 1174 | 1109 |
| LMArena Spanish | 1151 | 1173 |
Instruction Following Too close to call
Command R: 58.1 (#261), Llama 3-8B: 58.4 (#260)
| Benchmark | Command R | Llama 3-8B |
|---|---|---|
| LMArena Instruction Following | 1167 | 1127 |
| LiveBench Instruction Following | 55.6% | — |
Long Context Command R leads
Command R: 36.3 (#231), Llama 3-8B: 34.2 (#251)
| Benchmark | Command R | Llama 3-8B |
|---|---|---|
| LMArena Longer Query | 1198 | 1128 |
Writing & Preference Too close to call
Command R: 38.2 (#254), Llama 3-8B: 37.5 (#256)
| Benchmark | Command R | Llama 3-8B |
|---|---|---|
| LMArena Text | 1187 | 1166 |
| LMArena Creative Writing | 1170 | 1150 |
| LMArena Multi-Turn | 1163 | 1152 |
| LiveBench Language | 16.7% | — |
Frequently asked questions
Is Command R better than Llama 3-8B?
Command R is the stronger model overall, scoring 31.4 to 25.5 on the Noometry Index.
Is Command R or Llama 3-8B better for coding?
Llama 3-8B scores higher on coding benchmarks: 31.0 versus 29.3 in the Noometry coding category.
How many benchmarks do Command R and Llama 3-8B share?
21 benchmarks have published results for both models. Command R has 29 scored results on Noometry and Llama 3-8B has 34.