Model comparison
Command A vs Llama 4 Scout
Command A is the stronger model overall, scoring 36.5 to 27.7 on the Noometry Index. Llama 4 Scout costs 29× less per token, which makes it the better buy when Command A's lead doesn't matter for your workload.
Last verified . 23 shared benchmarks.
Cohere
MetaSummary
- They share 23 benchmarks with published results for both. Command A scores higher in 9 categories and Llama 4 Scout in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Command A leads 36.2 to 19.6.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 57.1% for Command A and 28.1% for Llama 4 Scout.
- Llama 4 Scout is cheaper at $0.10 / $0.30 per million input/output tokens, against $2.50 / $10 for Command A.
- Command A accepts more context: 256K tokens versus 128K.
Side by side
| Command A | Llama 4 Scout | |
|---|---|---|
| Provider | Cohere | Meta |
| Noometry Index | 36.5 | 27.7 |
| Released | 2025-03-13 | 2025-04-05 |
| Weights | Open | Open |
| Context window | 256K | 128K |
| Max output | 8K | 4K |
| Input $ / M tokens | $2.50 | $0.10 |
| Output $ / M tokens | $10 | $0.30 |
| Results tracked | 24 | 43 |
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 4 Scout: 20.2 (#339)
| Benchmark | Command A | Llama 4 Scout |
|---|---|---|
| LMArena Coding | 1330 | 1286 |
| SWE-bench Verified (bash only) | — | 9.1% |
| Aider Polyglot | 12% | — |
| SciCode | — | 17% |
| BigCodeBench Complete | — | 43.1% |
Agentic & Tool Use Command A leads
Command A: 35.9 (#40), Llama 4 Scout: 24.6 (#119)
| Benchmark | Command A | Llama 4 Scout |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | 28.1% |
Reasoning Command A leads
Command A: 18.3 (#283), Llama 4 Scout: 9.1 (#345)
| Benchmark | Command A | Llama 4 Scout |
|---|---|---|
| Kagi LLM Benchmark | 28.8% | 36.9% |
| LMArena Hard Prompts | 1326 | 1266 |
| DTBench | 61.3% | 57.9% |
| LMCA | 10.3% | 12% |
| ARC-AGI-2 | — | 0% |
| ARC-AGI-1 | — | 0.5% |
| CritPt | — | 0% |
| Epoch Capabilities Index | — | 129.64 |
| ForecastBench | — | 57.5 |
Math Command A leads
Command A: 36.2 (#171), Llama 4 Scout: 19.6 (#286)
| Benchmark | Command A | Llama 4 Scout |
|---|---|---|
| LMArena Math | 1300 | 1287 |
| OTIS Mock AIME 2024-2025 | — | 7.8% |
| Omni-MATH | — | 37.3% |
| MATH Level 5 | — | 62.3% |
| FrontierMath (Feb 2025 set) | — | 0% |
Knowledge Command A leads
Command A: 37.1 (#159), Llama 4 Scout: 31.9 (#217)
| Benchmark | Command A | Llama 4 Scout |
|---|---|---|
| Vectara Hallucination Rate | 9.3% | 7.7% |
| LMArena Expert | 1295 | 1235 |
| GPQA Diamond | — | 51.8% |
| MMLU-Pro | — | 74.2% |
| GPQA (HELM) | — | 50.7% |
Multimodal Not comparable
Command A: —, Llama 4 Scout: 32.2 (#102)
| Benchmark | Command A | Llama 4 Scout |
|---|---|---|
| LMArena Vision | — | 1118 |
| SpatialViz-Bench | — | 34.2% |
Multilingual Command A leads
Command A: 45.3 (#170), Llama 4 Scout: 41.0 (#212)
| Benchmark | Command A | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | 1313 | 1252 |
| LMArena Chinese | 1327 | 1255 |
| LMArena French | 1351 | 1282 |
| LMArena German | 1341 | 1272 |
| LMArena Japanese | 1285 | 1206 |
| LMArena Korean | 1285 | 1207 |
| LMArena Russian | 1314 | 1263 |
| LMArena Spanish | 1347 | 1278 |
Instruction Following Command A leads
Command A: 69.1 (#177), Llama 4 Scout: 65.8 (#217)
| Benchmark | Command A | Llama 4 Scout |
|---|---|---|
| LMArena Instruction Following | 1309 | 1248 |
| IFEval | — | 81.8% |
Long Context Command A leads
Command A: 40.6 (#151), Llama 4 Scout: 27.5 (#294)
| Benchmark | Command A | Llama 4 Scout |
|---|---|---|
| LMArena Longer Query | 1334 | 1265 |
| Fiction.LiveBench | — | 36% |
Writing & Preference Command A leads
Command A: 47.6 (#208), Llama 4 Scout: 37.0 (#261)
| Benchmark | Command A | Llama 4 Scout |
|---|---|---|
| LMArena Text | 1331 | 1279 |
| LMArena Creative Writing | 1319 | 1249 |
| EQ-Bench Creative Writing | 1145 | 783 |
| LMArena Multi-Turn | 1339 | 1280 |
| WildBench | — | 78% |
Frequently asked questions
Is Command A better than Llama 4 Scout?
Command A is the stronger model overall, scoring 36.5 to 27.7 on the Noometry Index. Llama 4 Scout costs 29× less per token, which makes it the better buy when Command A's lead doesn't matter for your workload.
Which is cheaper, Command A or Llama 4 Scout?
Llama 4 Scout is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Command A lists at $2.50 and $10.
Is Command A or Llama 4 Scout better for coding?
Command A scores higher on coding benchmarks: 27.2 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Command A does, with 256K tokens against 128K.
How many benchmarks do Command A and Llama 4 Scout share?
23 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Llama 4 Scout has 43.