Model comparison
Command A vs Llama 3-70B
Command A is the stronger model overall, scoring 36.5 to 28.8 on the Noometry Index.
Last verified . 19 shared benchmarks.
Cohere
MetaSummary
- They share 19 benchmarks with published results for both. Command A scores higher in 8 categories and Llama 3-70B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Command A leads 36.2 to 12.8.
- The biggest single-benchmark swing is DTBench: 61.3% for Command A and 54.2% for Llama 3-70B.
Side by side
| Command A | Llama 3-70B | |
|---|---|---|
| Provider | Cohere | Meta |
| Noometry Index | 36.5 | 28.8 |
| Released | 2025-03-13 | 2024-04-18 |
| Weights | Open | Open |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $2.50 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 24 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-70B leads
Command A: 27.2 (#322), Llama 3-70B: 35.8 (#218)
| Benchmark | Command A | Llama 3-70B |
|---|---|---|
| LMArena Coding | 1330 | 1206 |
| Aider Polyglot | 12% | — |
| BigCodeBench Instruct | — | 43.6% |
| BigCodeBench Complete | — | 54.5% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 69% |
Agentic & Tool Use Command A leads
Command A: 35.9 (#40), Llama 3-70B: 21.1 (#139)
| Benchmark | Command A | Llama 3-70B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
| Cybench | — | 5% |
Reasoning Too close to call
Command A: 18.3 (#283), Llama 3-70B: 18.0 (#288)
| Benchmark | Command A | Llama 3-70B |
|---|---|---|
| Kagi LLM Benchmark | 28.8% | 35.1% |
| LMArena Hard Prompts | 1326 | 1195 |
| DTBench | 61.3% | 54.2% |
| LMCA | 10.3% | — |
| Epoch Capabilities Index | — | 122.93 |
| ForecastBench | — | 57.1 |
| WinoGrande | — | 83.5% |
Math Command A leads
Command A: 36.2 (#171), Llama 3-70B: 12.8 (#305)
| Benchmark | Command A | Llama 3-70B |
|---|---|---|
| LMArena Math | 1300 | 1218 |
| OTIS Mock AIME 2024-2025 | — | 4.3% |
| MATH Level 5 | — | 22.6% |
Knowledge Command A leads
Command A: 37.1 (#159), Llama 3-70B: 20.8 (#277)
| Benchmark | Command A | Llama 3-70B |
|---|---|---|
| LMArena Expert | 1295 | 1149 |
| GPQA Diamond | — | 40.6% |
| Vectara Hallucination Rate | 9.3% | — |
| MMLU | — | 79.3% |
Multilingual Command A leads
Command A: 45.3 (#170), Llama 3-70B: 33.6 (#251)
| Benchmark | Command A | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 1313 | 1142 |
| LMArena Chinese | 1327 | 1114 |
| LMArena French | 1351 | 1232 |
| LMArena German | 1341 | 1169 |
| LMArena Japanese | 1285 | 1017 |
| LMArena Korean | 1285 | 1017 |
| LMArena Russian | 1314 | 1159 |
| LMArena Spanish | 1347 | 1241 |
Instruction Following Command A leads
Command A: 69.1 (#177), Llama 3-70B: 62.5 (#238)
| Benchmark | Command A | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1309 | 1194 |
Long Context Command A leads
Command A: 40.6 (#151), Llama 3-70B: 35.6 (#240)
| Benchmark | Command A | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | 1334 | 1174 |
Writing & Preference Command A leads
Command A: 47.6 (#208), Llama 3-70B: 42.8 (#231)
| Benchmark | Command A | Llama 3-70B |
|---|---|---|
| LMArena Text | 1331 | 1221 |
| LMArena Creative Writing | 1319 | 1210 |
| LMArena Multi-Turn | 1339 | 1223 |
| EQ-Bench Creative Writing | 1145 | — |
Frequently asked questions
Is Command A better than Llama 3-70B?
Command A is the stronger model overall, scoring 36.5 to 28.8 on the Noometry Index.
Is Command A or Llama 3-70B better for coding?
Llama 3-70B scores higher on coding benchmarks: 35.8 versus 27.2 in the Noometry coding category.
How many benchmarks do Command A and Llama 3-70B share?
19 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Llama 3-70B has 31.