Model comparison
Command A vs Llama 13b
Command A is the stronger model overall, scoring 36.5 to 24.4 on the Noometry Index.
Last verified . 8 shared benchmarks.
Cohere
MetaSummary
- They share 8 benchmarks with published results for both. Command A scores higher in 6 categories and Llama 13b in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Command A leads 47.6 to 13.8.
Side by side
| Command A | Llama 13b | |
|---|---|---|
| Provider | Cohere | Meta |
| Noometry Index | 36.5 | 24.4 |
| Released | 2025-03-13 | 2023-02-24 |
| Weights | Open | Open |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $2.50 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 24 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Command A leads
Command A: 27.2 (#322), Llama 13b: 21.4 (#337)
| Benchmark | Command A | Llama 13b |
|---|---|---|
| LMArena Coding | 1330 | 683 |
| Aider Polyglot | 12% | — |
Agentic & Tool Use Not comparable
Command A: 35.9 (#40), Llama 13b: —
| Benchmark | Command A | Llama 13b |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
Reasoning Command A leads
Command A: 18.3 (#283), Llama 13b: 14.0 (#329)
| Benchmark | Command A | Llama 13b |
|---|---|---|
| LMArena Hard Prompts | 1326 | 728 |
| Kagi LLM Benchmark | 28.8% | — |
| DTBench | 61.3% | — |
| LMCA | 10.3% | — |
| BIG-Bench Hard | — | 37.9% |
| Epoch Capabilities Index | — | 100.58 |
| HellaSwag | — | 79.2% |
| LAMBADA | — | 75.2% |
| PIQA | — | 80.1% |
| WinoGrande | — | 73% |
Math Command A leads
Command A: 36.2 (#171), Llama 13b: 26.7 (#256)
| Benchmark | Command A | Llama 13b |
|---|---|---|
| LMArena Math | 1300 | 838 |
| GSM8K | — | 20.6% |
Knowledge Not comparable
Command A: 37.1 (#159), Llama 13b: —
| Benchmark | Command A | Llama 13b |
|---|---|---|
| Vectara Hallucination Rate | 9.3% | — |
| LMArena Expert | 1295 | — |
| ARC (AI2) Challenge | — | 52.7% |
| BoolQ | — | 78.7% |
| MMLU | — | 47.7% |
| OpenBookQA | — | 56.4% |
| TriviaQA | — | 77.9% |
Multimodal Not comparable
Command A: —, Llama 13b: —
| Benchmark | Command A | Llama 13b |
|---|---|---|
| ScienceQA | — | 43.3% |
Multilingual Command A leads
Command A: 45.3 (#170), Llama 13b: 16.6 (#297)
| Benchmark | Command A | Llama 13b |
|---|---|---|
| LMArena Non-English | 1313 | 819 |
| LMArena Chinese | 1327 | — |
| LMArena French | 1351 | — |
| LMArena German | 1341 | — |
| LMArena Japanese | 1285 | — |
| LMArena Korean | 1285 | — |
| LMArena Russian | 1314 | — |
| LMArena Spanish | 1347 | — |
Instruction Following Command A leads
Command A: 69.1 (#177), Llama 13b: 36.7 (#305)
| Benchmark | Command A | Llama 13b |
|---|---|---|
| LMArena Instruction Following | 1309 | 781 |
Long Context Not comparable
Command A: 40.6 (#151), Llama 13b: —
| Benchmark | Command A | Llama 13b |
|---|---|---|
| LMArena Longer Query | 1334 | — |
Writing & Preference Command A leads
Command A: 47.6 (#208), Llama 13b: 13.8 (#312)
| Benchmark | Command A | Llama 13b |
|---|---|---|
| LMArena Text | 1331 | 834 |
| LMArena Creative Writing | 1319 | 794 |
| LMArena Multi-Turn | 1339 | 753 |
| EQ-Bench Creative Writing | 1145 | — |
Frequently asked questions
Is Command A better than Llama 13b?
Command A is the stronger model overall, scoring 36.5 to 24.4 on the Noometry Index.
Is Command A or Llama 13b better for coding?
Command A scores higher on coding benchmarks: 27.2 versus 21.4 in the Noometry coding category.
How many benchmarks do Command A and Llama 13b share?
8 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Llama 13b has 21.