# Command A vs Llama 2-70B

> Command A is the stronger model overall, scoring 36.5 to 24.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/command-a-vs-llama-2-70b
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Command A scores higher in 7 categories and Llama 2-70B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Command A leads 37.1 to 7.4.
- The biggest single-benchmark swing is DTBench: 61.3% for Command A and 41.6% for Llama 2-70B.

## Snapshot

| | Command A | Llama 2-70B |
|---|---|---|
| Provider | Cohere | Meta |
| Noometry Index | 36.5 | 24.4 |
| Rank | 215 | 349 |
| Context | 256K | — |
| Input $/M | $2.50 | — |
| Output $/M | $10 | — |
| Weights | Open | Open |

## Coding

- Command A: 27.2 (#322)
- Llama 2-70B: 31.4 (#286)

| Benchmark | Command A | Llama 2-70B |
|---|---|---|
| LMArena Coding | 1330 | 1079 |
| Aider Polyglot | 12% | — |

## Agentic & Tool Use

- Command A: 35.9 (#40)
- Llama 2-70B: —

| Benchmark | Command A | Llama 2-70B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |

## Reasoning

- Command A: 18.3 (#283)
- Llama 2-70B: 14.4 (#325)

| Benchmark | Command A | Llama 2-70B |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1073 |
| DTBench | 61.3% | 41.6% |
| Kagi LLM Benchmark | 28.8% | — |
| LMCA | 10.3% | — |
| BIG-Bench Hard | — | 64.9% |
| CommonsenseQA 2.0 | — | 50% |
| Epoch Capabilities Index | — | 113.79 |
| ForecastBench | — | 51.4 |
| HellaSwag | — | 85.3% |
| LAMBADA | — | 78.9% |
| PIQA | — | 82.8% |
| WinoGrande | — | 80.2% |

## Math

- Command A: 36.2 (#171)
- Llama 2-70B: 8.1 (#326)

| Benchmark | Command A | Llama 2-70B |
|---|---|---|
| LMArena Math | 1300 | 1091 |
| OTIS Mock AIME 2024-2025 | — | 0% |
| MATH Level 5 | — | 3.3% |
| GSM8K | — | 69.6% |

## Knowledge

- Command A: 37.1 (#159)
- Llama 2-70B: 7.4 (#310)

| Benchmark | Command A | Llama 2-70B |
|---|---|---|
| LMArena Expert | 1295 | 1039 |
| GPQA Diamond | — | 26.3% |
| Vectara Hallucination Rate | 9.3% | — |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 88.6% |
| MMLU | — | 69.9% |
| OpenBookQA | — | 60.2% |
| TriviaQA | — | 87.6% |

## Multilingual

- Command A: 45.3 (#170)
- Llama 2-70B: 27.7 (#274)

| Benchmark | Command A | Llama 2-70B |
|---|---|---|
| LMArena Non-English | 1313 | 1045 |
| LMArena Chinese | 1327 | 995 |
| LMArena French | 1351 | 1090 |
| LMArena German | 1341 | 1041 |
| LMArena Japanese | 1285 | 927 |
| LMArena Korean | 1285 | 964 |
| LMArena Russian | 1314 | 1083 |
| LMArena Spanish | 1347 | 1143 |

## Instruction Following

- Command A: 69.1 (#177)
- Llama 2-70B: 54.9 (#278)

| Benchmark | Command A | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | 1309 | 1071 |

## Long Context

- Command A: 40.6 (#151)
- Llama 2-70B: 32.3 (#270)

| Benchmark | Command A | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | 1334 | 1062 |

## Writing & Preference

- Command A: 47.6 (#208)
- Llama 2-70B: 32.3 (#279)

| Benchmark | Command A | Llama 2-70B |
|---|---|---|
| LMArena Text | 1331 | 1115 |
| LMArena Creative Writing | 1319 | 1075 |
| LMArena Multi-Turn | 1339 | 1088 |
| EQ-Bench Creative Writing | 1145 | — |

## FAQ

### Is Command A better than Llama 2-70B?

Command A is the stronger model overall, scoring 36.5 to 24.4 on the Noometry Index.

### Is Command A or Llama 2-70B better for coding?

Llama 2-70B scores higher on coding benchmarks: 31.4 versus 27.2 in the Noometry coding category.

### How many benchmarks do Command A and Llama 2-70B share?

18 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Llama 2-70B has 35.