# Command A vs Llama 3.2 90B

> Command A is the stronger model overall, scoring 35.9 to 27.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/command-a-vs-llama-3-2-90b
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where Command A leads 33.5 to 10.4.

## Snapshot

| | Command A | Llama 3.2 90B |
|---|---|---|
| Provider | Cohere | Meta |
| Noometry Index | 35.9 | 27.1 |
| Rank | 212 | 326 |
| Context | 256K | — |
| Input $/M | $2.50 | — |
| Output $/M | $10 | — |
| Weights | Open | Open |

## Coding

- Command A: 26.8 (#317)
- Llama 3.2 90B: —

| Benchmark | Command A | Llama 3.2 90B |
|---|---|---|
| Aider Polyglot | 12% | — |
| LMArena Coding | 1331 | — |

## Agentic & Tool Use

- Command A: 35.7 (#36)
- Llama 3.2 90B: 29.7 (#73)

| Benchmark | Command A | Llama 3.2 90B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
| BALROG | — | 27.3% |

## Reasoning

- Command A: 17.7 (#276)
- Llama 3.2 90B: 20.9 (#207)

| Benchmark | Command A | Llama 3.2 90B |
|---|---|---|
| Kagi LLM Benchmark | 28.8% | — |
| EnigmaEval | — | 0.4% |
| LMArena Hard Prompts | 1326 | — |
| DTBench | 61.3% | — |
| LMCA | 10.3% | — |
| Epoch Capabilities Index | — | 125.5 |

## Math

- Command A: 33.5 (#172)
- Llama 3.2 90B: 10.4 (#302)

| Benchmark | Command A | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.6% |
| LMArena Math | 1300 | — |
| MATH Level 5 | — | 39.4% |

## Knowledge

- Command A: 36.5 (#157)
- Llama 3.2 90B: 21.7 (#269)

| Benchmark | Command A | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | — | 41% |
| Vectara Hallucination Rate | 9.3% | — |
| LMArena Expert | 1295 | — |
| MMLU | — | 80.3% |

## Multimodal

- Command A: —
- Llama 3.2 90B: 24.9 (#119)

| Benchmark | Command A | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |

## Multilingual

- Command A: 45.5 (#166)
- Llama 3.2 90B: —

| Benchmark | Command A | Llama 3.2 90B |
|---|---|---|
| LMArena Non-English | 1313 | — |
| LMArena Chinese | 1327 | — |
| LMArena French | 1352 | — |
| LMArena German | 1341 | — |
| LMArena Japanese | 1283 | — |
| LMArena Korean | 1285 | — |
| LMArena Russian | 1314 | — |
| LMArena Spanish | 1346 | — |

## Instruction Following

- Command A: 69.3 (#172)
- Llama 3.2 90B: —

| Benchmark | Command A | Llama 3.2 90B |
|---|---|---|
| LMArena Instruction Following | 1309 | — |

## Long Context

- Command A: 40.6 (#147)
- Llama 3.2 90B: —

| Benchmark | Command A | Llama 3.2 90B |
|---|---|---|
| LMArena Longer Query | 1334 | — |

## Writing & Preference

- Command A: 47.8 (#204)
- Llama 3.2 90B: —

| Benchmark | Command A | Llama 3.2 90B |
|---|---|---|
| LMArena Text | 1331 | — |
| LMArena Creative Writing | 1319 | — |
| EQ-Bench Creative Writing | 1145 | — |
| LMArena Multi-Turn | 1338 | — |

## FAQ

### Is Command A better than Llama 3.2 90B?

Command A is the stronger model overall, scoring 35.9 to 27.1 on the Noometry Index.

### How many benchmarks do Command A and Llama 3.2 90B share?

0 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Llama 3.2 90B has 9.