Model comparison
Command R+ vs Llama 3.1-8B
Command R+ is the stronger model overall, scoring 32.4 to 23.0 on the Noometry Index. Llama 3.1-8B costs 76× less per token, which makes it the better buy when Command R+'s lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
Cohere
MetaSummary
- They share 25 benchmarks with published results for both. Command R+ scores higher in 7 categories and Llama 3.1-8B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Command R+ leads 36.4 to 8.0.
- Llama 3.1-8B is cheaper at $0.05 / $0.08 per million input/output tokens, against $2.50 / $10 for Command R+.
Side by side
| Command R+ | Llama 3.1-8B | |
|---|---|---|
| Provider | Cohere | Meta |
| Noometry Index | 32.4 | 23.0 |
| Released | 2024-08-30 | 2024-07-23 |
| Weights | Open | Open |
| Context window | 128K | 128K |
| Max output | 4K | 4K |
| Input $ / M tokens | $2.50 | $0.05 |
| Output $ / M tokens | $10 | $0.08 |
| Results tracked | 34 | 43 |
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 3.1-8B: 20.2 (#340)
| Benchmark | Command R+ | Llama 3.1-8B |
|---|---|---|
| BigCodeBench Instruct | 33.8% | 32.8% |
| LMArena Coding | 1187 | 1195 |
| BigCodeBench Complete | 41.9% | 40.5% |
| HumanEval+ | 56.7% | 62.8% |
| MBPP+ | 63.5% | 55.6% |
| SciCode | — | 13.2% |
| WeirdML | — | 1.7% |
| LiveBench Coding | 19.1% | — |
Agentic & Tool Use Not comparable
Command R+: —, Llama 3.1-8B: 22.5 (#131)
| Benchmark | Command R+ | Llama 3.1-8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 25.8% |
| BALROG | — | 15.1% |
Reasoning Llama 3.1-8B leads
Command R+: 9.2 (#344), Llama 3.1-8B: 14.9 (#321)
| Benchmark | Command R+ | Llama 3.1-8B |
|---|---|---|
| LMArena Hard Prompts | 1186 | 1175 |
| DTBench | 54.9% | 50.9% |
| LMCA | 5% | 5.4% |
| Epoch Capabilities Index | 119.34 | 116.57 |
| SimpleBench | 17.4% | — |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | 24.8% | — |
| LiveBench Data Analysis | 38.1% | — |
| LiveBench | 31.8% | — |
| PIQA | — | 81.2% |
Math Command R+ leads
Command R+: 28.9 (#242), Llama 3.1-8B: 10.2 (#317)
| Benchmark | Command R+ | Llama 3.1-8B |
|---|---|---|
| LMArena Math | 1188 | 1179 |
| OTIS Mock AIME 2024-2025 | — | 1.7% |
| Omni-MATH | — | 13.7% |
| LiveBench Math | 21.3% | — |
| MATH Level 5 | — | 22.9% |
| GSM8K | — | 82.4% |
Knowledge Command R+ leads
Command R+: 36.4 (#169), Llama 3.1-8B: 8.0 (#307)
| Benchmark | Command R+ | Llama 3.1-8B |
|---|---|---|
| LMArena Expert | 1174 | 1144 |
| MMLU | 69.4% | 56.1% |
| GPQA Diamond | — | 27% |
| MMLU-Pro | — | 40.6% |
| Vectara Hallucination Rate | 6.9% | — |
| GPQA (HELM) | — | 24.7% |
| BoolQ | — | 82.8% |
Multilingual Command R+ leads
Command R+: 38.6 (#227), Llama 3.1-8B: 34.0 (#249)
| Benchmark | Command R+ | Llama 3.1-8B |
|---|---|---|
| LMArena Non-English | 1216 | 1148 |
| LMArena Chinese | 1226 | 1151 |
| LMArena French | 1209 | 1177 |
| LMArena German | 1216 | 1144 |
| LMArena Japanese | 1166 | 1061 |
| LMArena Korean | 1138 | 1053 |
| LMArena Russian | 1227 | 1158 |
| LMArena Spanish | 1189 | 1169 |
Instruction Following Command R+ leads
Command R+: 60.0 (#254), Llama 3.1-8B: 58.9 (#258)
| Benchmark | Command R+ | Llama 3.1-8B |
|---|---|---|
| LMArena Instruction Following | 1197 | 1159 |
| LiveBench Instruction Following | 57.6% | — |
| IFEval | — | 74.3% |
Long Context Command R+ leads
Command R+: 37.3 (#219), Llama 3.1-8B: 35.8 (#238)
| Benchmark | Command R+ | Llama 3.1-8B |
|---|---|---|
| LMArena Longer Query | 1230 | 1182 |
Writing & Preference Command R+ leads
Command R+: 43.5 (#228), Llama 3.1-8B: 29.7 (#290)
| Benchmark | Command R+ | Llama 3.1-8B |
|---|---|---|
| LMArena Text | 1229 | 1187 |
| LMArena Creative Writing | 1235 | 1154 |
| LMArena Multi-Turn | 1213 | 1172 |
| EQ-Bench Creative Writing | — | 713 |
| WildBench | — | 68.7% |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than Llama 3.1-8B?
Command R+ is the stronger model overall, scoring 32.4 to 23.0 on the Noometry Index. Llama 3.1-8B costs 76× 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 Llama 3.1-8B?
Llama 3.1-8B is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Command R+ lists at $2.50 and $10.
Is Command R+ or Llama 3.1-8B better for coding?
Command R+ scores higher on coding benchmarks: 29.1 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do Command R+ and Llama 3.1-8B share?
25 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Llama 3.1-8B has 43.