# Command R vs DeepSeek-V3.1-Terminus

> DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 31.0 on the Noometry Index. Command R costs 1.8× less per token, which makes it the better buy when DeepSeek-V3.1-Terminus's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/command-r-vs-deepseek-v3-1-terminus
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Command R 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 writing & preference, where DeepSeek-V3.1-Terminus leads 61.3 to 38.4.
- The biggest single-benchmark swing is DTBench: 46.4% for Command R and 81.3% for DeepSeek-V3.1-Terminus.
- Command R is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.30 / $1 for DeepSeek-V3.1-Terminus.
- DeepSeek-V3.1-Terminus accepts more context: 164K tokens versus 128K.

## Snapshot

| | Command R | DeepSeek-V3.1-Terminus |
|---|---|---|
| Provider | Cohere | DeepSeek |
| Noometry Index | 31.0 | 42.6 |
| Rank | 267 | 96 |
| Context | 128K | 164K |
| Input $/M | $0.15 | $0.30 |
| Output $/M | $0.60 | $1 |
| Weights | Open | Open |

## Coding

- Command R: 28.8 (#301)
- DeepSeek-V3.1-Terminus: 41.5 (#114)

| Benchmark | Command R | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Coding | 1170 | 1426 |
| SciCode | — | 40.6% |
| BigCodeBench Instruct | 37.1% | — |
| LiveBench Coding | 17.9% | — |
| BigCodeBench Complete | 45.2% | — |
| ALE-Bench | — | 745.17 |

## Reasoning

- Command R: 13.3 (#329)
- DeepSeek-V3.1-Terminus: 25.7 (#126)

| Benchmark | Command R | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Hard Prompts | 1164 | 1427 |
| DTBench | 46.4% | 81.3% |
| LMCA | 9.2% | 28.6% |
| Kagi LLM Benchmark | — | 57.4% |
| CritPt | — | 1.7% |
| LiveBench Reasoning | 21.9% | — |
| LiveBench Data Analysis | 33.3% | — |
| LiveBench | 27.5% | — |

## Math

- Command R: 25.8 (#244)
- DeepSeek-V3.1-Terminus: 35.7 (#138)

| Benchmark | Command R | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Math | 1155 | 1402 |
| LiveBench Math | 19.4% | — |

## Knowledge

- Command R: 30.5 (#219)
- DeepSeek-V3.1-Terminus: —

| Benchmark | Command R | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Expert | 1138 | — |
| MMLU | 65.2% | — |

## Multilingual

- Command R: 35.9 (#240)
- DeepSeek-V3.1-Terminus: 52.3 (#87)

| Benchmark | Command R | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Non-English | 1174 | 1407 |
| LMArena Russian | 1174 | 1434 |
| LMArena Chinese | 1182 | — |
| LMArena French | 1161 | — |
| LMArena German | 1176 | — |
| LMArena Japanese | 1143 | — |
| LMArena Korean | 1162 | — |
| LMArena Spanish | 1150 | — |

## Instruction Following

- Command R: 58.3 (#256)
- DeepSeek-V3.1-Terminus: 74.4 (#96)

| Benchmark | Command R | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Instruction Following | 1167 | 1406 |
| LiveBench Instruction Following | 55.6% | — |

## Long Context

- Command R: 36.3 (#226)
- DeepSeek-V3.1-Terminus: 43.5 (#88)

| Benchmark | Command R | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Longer Query | 1198 | 1426 |

## Writing & Preference

- Command R: 38.4 (#248)
- DeepSeek-V3.1-Terminus: 61.3 (#87)

| Benchmark | Command R | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Text | 1187 | 1420 |
| LMArena Creative Writing | 1170 | 1404 |
| LMArena Multi-Turn | 1163 | 1411 |
| LiveBench Language | 16.7% | — |

## FAQ

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

DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 31.0 on the Noometry Index. Command R costs 1.8× less per token, which makes it the better buy when DeepSeek-V3.1-Terminus's lead doesn't matter for your workload.

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

Command R is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; DeepSeek-V3.1-Terminus lists at $0.30 and $1.

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

DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 28.8 in the Noometry coding category.

### Which has the bigger context window?

DeepSeek-V3.1-Terminus does, with 164K tokens against 128K.

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

12 benchmarks have published results for both models. Command R has 29 scored results on Noometry and DeepSeek-V3.1-Terminus has 16.