Model comparison
Command A vs Llama 3.1-405B
Command A is the stronger model overall, scoring 36.5 to 30.7 on the Noometry Index.
Last verified . 20 shared benchmarks.
Cohere
MetaSummary
- They share 20 benchmarks with published results for both. Command A scores higher in 8 categories and Llama 3.1-405B in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Command A leads 36.2 to 18.4.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 28.8% for Command A and 45% for Llama 3.1-405B.
Side by side
| Command A | Llama 3.1-405B | |
|---|---|---|
| Provider | Cohere | Meta |
| Noometry Index | 36.5 | 30.7 |
| Released | 2025-03-13 | 2024-07-23 |
| Weights | Open | Open |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $2.50 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 24 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3.1-405B leads
Command A: 27.2 (#322), Llama 3.1-405B: 33.1 (#262)
| Benchmark | Command A | Llama 3.1-405B |
|---|---|---|
| LMArena Coding | 1330 | 1291 |
| Aider Polyglot | 12% | — |
| WeirdML | — | 21.4% |
Agentic & Tool Use Command A leads
Command A: 35.9 (#40), Llama 3.1-405B: 21.0 (#140)
| Benchmark | Command A | Llama 3.1-405B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
| TheAgentCompany | — | 7.4% |
| Cybench | — | 7.5% |
Reasoning Command A leads
Command A: 18.3 (#283), Llama 3.1-405B: 16.8 (#300)
| Benchmark | Command A | Llama 3.1-405B |
|---|---|---|
| Kagi LLM Benchmark | 28.8% | 45% |
| LMArena Hard Prompts | 1326 | 1269 |
| DTBench | 61.3% | 61.4% |
| SimpleBench | — | 23% |
| LMCA | 10.3% | — |
| BIG-Bench Hard | — | 82.9% |
| Epoch Capabilities Index | — | 128.75 |
| ForecastBench | — | 59.9 |
| HellaSwag | — | 89.2% |
| PIQA | — | 85.9% |
| WinoGrande | — | 89.2% |
Math Command A leads
Command A: 36.2 (#171), Llama 3.1-405B: 18.4 (#290)
| Benchmark | Command A | Llama 3.1-405B |
|---|---|---|
| LMArena Math | 1300 | 1281 |
| OTIS Mock AIME 2024-2025 | — | 9.7% |
| Omni-MATH | — | 24.9% |
| MATH Level 5 | — | 49.8% |
Knowledge Command A leads
Command A: 37.1 (#159), Llama 3.1-405B: 30.4 (#227)
| Benchmark | Command A | Llama 3.1-405B |
|---|---|---|
| LMArena Expert | 1295 | 1243 |
| GPQA Diamond | — | 50.9% |
| MMLU-Pro | — | 72.3% |
| Confabulations | — | 17.6% |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | — | 52.2% |
| ARC (AI2) Challenge | — | 95.3% |
| MMLU | — | 84.5% |
| TriviaQA | — | 82.7% |
Multilingual Command A leads
Command A: 45.3 (#170), Llama 3.1-405B: 40.7 (#214)
| Benchmark | Command A | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | 1313 | 1248 |
| LMArena Chinese | 1327 | 1242 |
| LMArena French | 1351 | 1279 |
| LMArena German | 1341 | 1252 |
| LMArena Japanese | 1285 | 1208 |
| LMArena Korean | 1285 | 1184 |
| LMArena Russian | 1314 | 1265 |
| LMArena Spanish | 1347 | 1260 |
Instruction Following Command A leads
Command A: 69.1 (#177), Llama 3.1-405B: 65.9 (#214)
| Benchmark | Command A | Llama 3.1-405B |
|---|---|---|
| LMArena Instruction Following | 1309 | 1259 |
| IFEval | — | 81.1% |
Long Context Command A leads
Command A: 40.6 (#151), Llama 3.1-405B: 38.4 (#197)
| Benchmark | Command A | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | 1334 | 1266 |
Writing & Preference Command A leads
Command A: 47.6 (#208), Llama 3.1-405B: 38.9 (#251)
| Benchmark | Command A | Llama 3.1-405B |
|---|---|---|
| LMArena Text | 1331 | 1284 |
| LMArena Creative Writing | 1319 | 1262 |
| EQ-Bench Creative Writing | 1145 | 870 |
| LMArena Multi-Turn | 1339 | 1297 |
| WildBench | — | 78.3% |
Frequently asked questions
Is Command A better than Llama 3.1-405B?
Command A is the stronger model overall, scoring 36.5 to 30.7 on the Noometry Index.
Is Command A or Llama 3.1-405B better for coding?
Llama 3.1-405B scores higher on coding benchmarks: 33.1 versus 27.2 in the Noometry coding category.
How many benchmarks do Command A and Llama 3.1-405B share?
20 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Llama 3.1-405B has 42.