# Command A vs DeepSeek-V3.1-Terminus

> DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 35.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/command-a-vs-deepseek-v3-1-terminus
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Command A scores higher in 0 categories and DeepSeek-V3.1-Terminus in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V3.1-Terminus leads 41.5 to 26.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 28.8% for Command A and 57.4% for DeepSeek-V3.1-Terminus.
- DeepSeek-V3.1-Terminus is cheaper at $0.30 / $1 per million input/output tokens, against $2.50 / $10 for Command A.
- Command A accepts more context: 256K tokens versus 164K.

## Snapshot

| | Command A | DeepSeek-V3.1-Terminus |
|---|---|---|
| Provider | Cohere | DeepSeek |
| Noometry Index | 35.9 | 42.6 |
| Rank | 212 | 96 |
| Context | 256K | 164K |
| Input $/M | $2.50 | $0.30 |
| Output $/M | $10 | $1 |
| Weights | Open | Open |

## Coding

- Command A: 26.8 (#317)
- DeepSeek-V3.1-Terminus: 41.5 (#114)

| Benchmark | Command A | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Coding | 1331 | 1426 |
| Aider Polyglot | 12% | — |
| SciCode | — | 40.6% |
| ALE-Bench | — | 745.17 |

## Agentic & Tool Use

- Command A: 35.7 (#36)
- DeepSeek-V3.1-Terminus: —

| Benchmark | Command A | DeepSeek-V3.1-Terminus |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |

## Reasoning

- Command A: 17.7 (#276)
- DeepSeek-V3.1-Terminus: 25.7 (#126)

| Benchmark | Command A | DeepSeek-V3.1-Terminus |
|---|---|---|
| Kagi LLM Benchmark | 28.8% | 57.4% |
| LMArena Hard Prompts | 1326 | 1427 |
| DTBench | 61.3% | 81.3% |
| LMCA | 10.3% | 28.6% |
| CritPt | — | 1.7% |

## Math

- Command A: 33.5 (#172)
- DeepSeek-V3.1-Terminus: 35.7 (#138)

| Benchmark | Command A | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Math | 1300 | 1402 |

## Knowledge

- Command A: 36.5 (#157)
- DeepSeek-V3.1-Terminus: —

| Benchmark | Command A | DeepSeek-V3.1-Terminus |
|---|---|---|
| Vectara Hallucination Rate | 9.3% | — |
| LMArena Expert | 1295 | — |

## Multilingual

- Command A: 45.5 (#166)
- DeepSeek-V3.1-Terminus: 52.3 (#87)

| Benchmark | Command A | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Non-English | 1313 | 1407 |
| LMArena Russian | 1314 | 1434 |
| LMArena Chinese | 1327 | — |
| LMArena French | 1352 | — |
| LMArena German | 1341 | — |
| LMArena Japanese | 1283 | — |
| LMArena Korean | 1285 | — |
| LMArena Spanish | 1346 | — |

## Instruction Following

- Command A: 69.3 (#172)
- DeepSeek-V3.1-Terminus: 74.4 (#96)

| Benchmark | Command A | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Instruction Following | 1309 | 1406 |

## Long Context

- Command A: 40.6 (#147)
- DeepSeek-V3.1-Terminus: 43.5 (#88)

| Benchmark | Command A | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Longer Query | 1334 | 1426 |

## Writing & Preference

- Command A: 47.8 (#204)
- DeepSeek-V3.1-Terminus: 61.3 (#87)

| Benchmark | Command A | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Text | 1331 | 1420 |
| LMArena Creative Writing | 1319 | 1404 |
| LMArena Multi-Turn | 1338 | 1411 |
| EQ-Bench Creative Writing | 1145 | — |

## FAQ

### Is Command A better than DeepSeek-V3.1-Terminus?

DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 35.9 on the Noometry Index.

### Which is cheaper, Command A or DeepSeek-V3.1-Terminus?

DeepSeek-V3.1-Terminus is cheaper. It lists at $0.30 per million input tokens and $1 per million output tokens; Command A lists at $2.50 and $10.

### Is Command A or DeepSeek-V3.1-Terminus better for coding?

DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 26.8 in the Noometry coding category.

### Which has the bigger context window?

Command A does, with 256K tokens against 164K.

### How many benchmarks do Command A and DeepSeek-V3.1-Terminus share?

13 benchmarks have published results for both models. Command A has 24 scored results on Noometry and DeepSeek-V3.1-Terminus has 16.