Model comparison
Command A vs Llama 2-13B
Command A is the stronger model overall, scoring 36.5 to 29.6 on the Noometry Index.
Last verified . 18 shared benchmarks.
Cohere
MetaSummary
- They share 18 benchmarks with published results for both. Command A scores higher in 7 categories and Llama 2-13B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Command A leads 45.3 to 26.5.
- The biggest single-benchmark swing is DTBench: 61.3% for Command A and 42.2% for Llama 2-13B.
Side by side
| Command A | Llama 2-13B | |
|---|---|---|
| Provider | Cohere | Meta |
| Noometry Index | 36.5 | 29.6 |
| Released | 2025-03-13 | 2023-07-18 |
| Weights | Open | Open |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $2.50 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 24 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 2-13B leads
Command A: 27.2 (#322), Llama 2-13B: 30.9 (#291)
| Benchmark | Command A | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1330 | 1062 |
| Aider Polyglot | 12% | — |
Agentic & Tool Use Not comparable
Command A: 35.9 (#40), Llama 2-13B: —
| Benchmark | Command A | Llama 2-13B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
Reasoning Command A leads
Command A: 18.3 (#283), Llama 2-13B: 12.8 (#337)
| Benchmark | Command A | Llama 2-13B |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1051 |
| DTBench | 61.3% | 42.2% |
| Kagi LLM Benchmark | 28.8% | — |
| Chess Puzzles | — | 0% |
| LMCA | 10.3% | — |
| BIG-Bench Hard | — | 58.2% |
| Epoch Capabilities Index | — | 106.17 |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| PIQA | — | 80.8% |
| WinoGrande | — | 72.8% |
Math Command A leads
Command A: 36.2 (#171), Llama 2-13B: 31.1 (#229)
| Benchmark | Command A | Llama 2-13B |
|---|---|---|
| LMArena Math | 1300 | 1065 |
| GSM8K | — | 36.9% |
Knowledge Command A leads
Command A: 37.1 (#159), Llama 2-13B: 28.1 (#249)
| Benchmark | Command A | Llama 2-13B |
|---|---|---|
| LMArena Expert | 1295 | 1030 |
| Vectara Hallucination Rate | 9.3% | — |
| ARC (AI2) Challenge | — | 60.3% |
| BoolQ | — | 82.4% |
| MMLU | — | 55.6% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
Command A: —, Llama 2-13B: —
| Benchmark | Command A | Llama 2-13B |
|---|---|---|
| ScienceQA | — | 55.8% |
Multilingual Command A leads
Command A: 45.3 (#170), Llama 2-13B: 26.5 (#279)
| Benchmark | Command A | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1313 | 1024 |
| LMArena Chinese | 1327 | 1001 |
| LMArena French | 1351 | 1044 |
| LMArena German | 1341 | 1009 |
| LMArena Japanese | 1285 | 894 |
| LMArena Korean | 1285 | 953 |
| LMArena Russian | 1314 | 1055 |
| LMArena Spanish | 1347 | 1087 |
Instruction Following Command A leads
Command A: 69.1 (#177), Llama 2-13B: 53.3 (#287)
| Benchmark | Command A | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1309 | 1045 |
Long Context Command A leads
Command A: 40.6 (#151), Llama 2-13B: 32.3 (#269)
| Benchmark | Command A | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 1334 | 1064 |
Writing & Preference Command A leads
Command A: 47.6 (#208), Llama 2-13B: 29.8 (#289)
| Benchmark | Command A | Llama 2-13B |
|---|---|---|
| LMArena Text | 1331 | 1084 |
| LMArena Creative Writing | 1319 | 1047 |
| LMArena Multi-Turn | 1339 | 1050 |
| EQ-Bench Creative Writing | 1145 | — |
Frequently asked questions
Is Command A better than Llama 2-13B?
Command A is the stronger model overall, scoring 36.5 to 29.6 on the Noometry Index.
Is Command A or Llama 2-13B better for coding?
Llama 2-13B scores higher on coding benchmarks: 30.9 versus 27.2 in the Noometry coding category.
How many benchmarks do Command A and Llama 2-13B share?
18 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Llama 2-13B has 32.