# Command A vs DeepSeek LLM 67B

> Command A is the stronger model overall, scoring 35.9 to 24.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/command-a-vs-deepseek-llm-67b
- Last updated: 2026-10-10
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. Command A scores higher in 7 categories and DeepSeek LLM 67B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Command A leads 36.5 to 7.1.

## Snapshot

| | Command A | DeepSeek LLM 67B |
|---|---|---|
| Provider | Cohere | DeepSeek |
| Noometry Index | 35.9 | 24.8 |
| Rank | 212 | 341 |
| Context | 256K | — |
| Input $/M | $2.50 | — |
| Output $/M | $10 | — |
| Weights | Open | Open |

## Coding

- Command A: 26.8 (#317)
- DeepSeek LLM 67B: 31.3 (#273)

| Benchmark | Command A | DeepSeek LLM 67B |
|---|---|---|
| LMArena Coding | 1331 | 1096 |
| Aider Polyglot | 12% | — |

## Agentic & Tool Use

- Command A: 35.7 (#36)
- DeepSeek LLM 67B: —

| Benchmark | Command A | DeepSeek LLM 67B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |

## Reasoning

- Command A: 17.7 (#276)
- DeepSeek LLM 67B: 15.9 (#300)

| Benchmark | Command A | DeepSeek LLM 67B |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1070 |
| Kagi LLM Benchmark | 28.8% | — |
| Chess Puzzles | — | 0% |
| DTBench | 61.3% | — |
| LMCA | 10.3% | — |
| Epoch Capabilities Index | — | 110.54 |

## Math

- Command A: 33.5 (#172)
- DeepSeek LLM 67B: 8.1 (#318)

| Benchmark | Command A | DeepSeek LLM 67B |
|---|---|---|
| LMArena Math | 1300 | 1108 |
| OTIS Mock AIME 2024-2025 | — | 0.8% |
| MATH Level 5 | — | 6.4% |

## Knowledge

- Command A: 36.5 (#157)
- DeepSeek LLM 67B: 7.1 (#308)

| Benchmark | Command A | DeepSeek LLM 67B |
|---|---|---|
| GPQA Diamond | — | 24.6% |
| Vectara Hallucination Rate | 9.3% | — |
| LMArena Expert | 1295 | — |

## Multilingual

- Command A: 45.5 (#166)
- DeepSeek LLM 67B: 29.5 (#262)

| Benchmark | Command A | DeepSeek LLM 67B |
|---|---|---|
| LMArena Non-English | 1313 | 1073 |
| LMArena Chinese | 1327 | 1132 |
| 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)
- DeepSeek LLM 67B: 55.7 (#272)

| Benchmark | Command A | DeepSeek LLM 67B |
|---|---|---|
| LMArena Instruction Following | 1309 | 1079 |

## Long Context

- Command A: 40.6 (#147)
- DeepSeek LLM 67B: 33.1 (#260)

| Benchmark | Command A | DeepSeek LLM 67B |
|---|---|---|
| LMArena Longer Query | 1334 | 1092 |

## Writing & Preference

- Command A: 47.8 (#204)
- DeepSeek LLM 67B: 31.8 (#277)

| Benchmark | Command A | DeepSeek LLM 67B |
|---|---|---|
| LMArena Text | 1331 | 1105 |
| LMArena Creative Writing | 1319 | 1067 |
| LMArena Multi-Turn | 1338 | 1082 |
| EQ-Bench Creative Writing | 1145 | — |

## FAQ

### Is Command A better than DeepSeek LLM 67B?

Command A is the stronger model overall, scoring 35.9 to 24.8 on the Noometry Index.

### Is Command A or DeepSeek LLM 67B better for coding?

DeepSeek LLM 67B scores higher on coding benchmarks: 31.3 versus 26.8 in the Noometry coding category.

### How many benchmarks do Command A and DeepSeek LLM 67B share?

10 benchmarks have published results for both models. Command A has 24 scored results on Noometry and DeepSeek LLM 67B has 15.