Model comparison
Command R vs Llama 3.1-405B
Command R and Llama 3.1-405B score almost the same on the Noometry Index (31.0 vs 30.4), so choose on price, context window or the category you care about most.
Last verified . 19 shared benchmarks.
Cohere
MetaSummary
- They share 19 benchmarks with published results for both. Command R scores higher in 2 categories and Llama 3.1-405B in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Command R leads 25.8 to 17.3.
- The biggest single-benchmark swing is DTBench: 46.4% for Command R and 61.4% for Llama 3.1-405B.
Side by side
| Command R | Llama 3.1-405B | |
|---|---|---|
| Provider | Cohere | Meta |
| Noometry Index | 31.0 | 30.4 |
| Released | 2024-08-30 | 2024-07-23 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 29 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3.1-405B leads
Command R: 28.8 (#301), Llama 3.1-405B: 32.7 (#257)
| Benchmark | Command R | Llama 3.1-405B |
|---|---|---|
| LMArena Coding | 1170 | 1291 |
| WeirdML | — | 21.4% |
| BigCodeBench Instruct | 37.1% | — |
| LiveBench Coding | 17.9% | — |
| BigCodeBench Complete | 45.2% | — |
Agentic & Tool Use Not comparable
Command R: —, Llama 3.1-405B: 20.9 (#131)
| Benchmark | Command R | Llama 3.1-405B |
|---|---|---|
| TheAgentCompany | — | 7.4% |
| Cybench | — | 7.5% |
Reasoning Llama 3.1-405B leads
Command R: 13.3 (#329), Llama 3.1-405B: 16.4 (#293)
| Benchmark | Command R | Llama 3.1-405B |
|---|---|---|
| LMArena Hard Prompts | 1164 | 1270 |
| DTBench | 46.4% | 61.4% |
| SimpleBench | — | 23% |
| Kagi LLM Benchmark | — | 45% |
| LiveBench Reasoning | 21.9% | — |
| LiveBench Data Analysis | 33.3% | — |
| LMCA | 9.2% | — |
| BIG-Bench Hard | — | 82.9% |
| Epoch Capabilities Index | — | 128.76 |
| ForecastBench | — | 59.9 |
| HellaSwag | — | 89.2% |
| LiveBench | 27.5% | — |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |
Math Command R leads
Command R: 25.8 (#244), Llama 3.1-405B: 17.3 (#283)
| Benchmark | Command R | Llama 3.1-405B |
|---|---|---|
| LMArena Math | 1155 | 1281 |
| OTIS Mock AIME 2024-2025 | — | 9.7% |
| Omni-MATH | — | 24.9% |
| LiveBench Math | 19.4% | — |
| MATH Level 5 | — | 49.8% |
Knowledge Too close to call
Command R: 30.5 (#219), Llama 3.1-405B: 30.4 (#221)
| Benchmark | Command R | Llama 3.1-405B |
|---|---|---|
| LMArena Expert | 1138 | 1243 |
| MMLU | 65.2% | 84.5% |
| GPQA Diamond | — | 50.9% |
| MMLU-Pro | — | 72.3% |
| Confabulations | — | 17.6% |
| GPQA (HELM) | — | 52.2% |
| ARC (AI2) Challenge | — | 95.3% |
| TriviaQA | — | 82.7% |
Multilingual Llama 3.1-405B leads
Command R: 35.9 (#240), Llama 3.1-405B: 40.9 (#209)
| Benchmark | Command R | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1174 | 1248 |
| LMArena Chinese | 1182 | 1242 |
| LMArena French | 1161 | 1278 |
| LMArena German | 1176 | 1252 |
| LMArena Japanese | 1143 | 1208 |
| LMArena Korean | 1162 | 1184 |
| LMArena Russian | 1174 | 1265 |
| LMArena Spanish | 1150 | 1259 |
Instruction Following Llama 3.1-405B leads
Command R: 58.3 (#256), Llama 3.1-405B: 66.1 (#209)
| Benchmark | Command R | Llama 3.1-405B |
|---|---|---|
| LMArena Instruction Following | 1167 | 1259 |
| LiveBench Instruction Following | 55.6% | — |
| IFEval | — | 81.1% |
Long Context Llama 3.1-405B leads
Command R: 36.3 (#226), Llama 3.1-405B: 38.4 (#192)
| Benchmark | Command R | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1198 | 1266 |
Writing & Preference Too close to call
Command R: 38.4 (#248), Llama 3.1-405B: 39.1 (#246)
| Benchmark | Command R | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1187 | 1284 |
| LMArena Creative Writing | 1170 | 1262 |
| LMArena Multi-Turn | 1163 | 1297 |
| EQ-Bench Creative Writing | — | 870 |
| WildBench | — | 78.3% |
| LiveBench Language | 16.7% | — |
Frequently asked questions
Is Command R better than Llama 3.1-405B?
Command R and Llama 3.1-405B score almost the same on the Noometry Index (31.0 vs 30.4), so choose on price, context window or the category you care about most.
Is Command R or Llama 3.1-405B better for coding?
Llama 3.1-405B scores higher on coding benchmarks: 32.7 versus 28.8 in the Noometry coding category.
How many benchmarks do Command R and Llama 3.1-405B share?
19 benchmarks have published results for both models. Command R has 29 scored results on Noometry and Llama 3.1-405B has 42.