# Command R+ vs DeepSeek-V3.1

> DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 32.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/command-r-plus-vs-deepseek-v3-1
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. Command R+ scores higher in 1 category and DeepSeek-V3.1 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek-V3.1 leads 27.9 to 9.2.
- The biggest single-benchmark swing is DTBench: 54.9% for Command R+ and 82.7% for DeepSeek-V3.1.
- DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $2.50 / $10 for Command R+.
- DeepSeek-V3.1 accepts more context: 164K tokens versus 128K.

## Snapshot

| | Command R+ | DeepSeek-V3.1 |
|---|---|---|
| Provider | Cohere | DeepSeek |
| Noometry Index | 32.4 | 42.8 |
| Rank | 257 | 108 |
| Context | 128K | 164K |
| Input $/M | $2.50 | $0.25 |
| Output $/M | $10 | $0.95 |
| Weights | Open | Open |

## Coding

- Command R+: 29.1 (#309)
- DeepSeek-V3.1: 40.3 (#144)

| Benchmark | Command R+ | DeepSeek-V3.1 |
|---|---|---|
| LMArena Coding | 1187 | 1417 |
| WeirdML | — | 38.4% |
| BigCodeBench Instruct | 33.8% | — |
| LiveBench Coding | 19.1% | — |
| BigCodeBench Complete | 41.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |

## Reasoning

- Command R+: 9.2 (#344)
- DeepSeek-V3.1: 27.9 (#110)

| Benchmark | Command R+ | DeepSeek-V3.1 |
|---|---|---|
| SimpleBench | 17.4% | 40% |
| LMArena Hard Prompts | 1186 | 1417 |
| DTBench | 54.9% | 82.7% |
| LMCA | 5% | 24.3% |
| Epoch Capabilities Index | 119.34 | 139.92 |
| Kagi LLM Benchmark | — | 53.2% |
| LiveBench Reasoning | 24.8% | — |
| LiveBench Data Analysis | 38.1% | — |
| ForecastBench | — | 58 |
| LiveBench | 31.8% | — |

## Math

- Command R+: 28.9 (#242)
- DeepSeek-V3.1: 38.9 (#122)

| Benchmark | Command R+ | DeepSeek-V3.1 |
|---|---|---|
| LMArena Math | 1188 | 1420 |
| LiveBench Math | 21.3% | — |

## Knowledge

- Command R+: 36.4 (#169)
- DeepSeek-V3.1: 43.7 (#90)

| Benchmark | Command R+ | DeepSeek-V3.1 |
|---|---|---|
| Vectara Hallucination Rate | 6.9% | 5.5% |
| LMArena Expert | 1174 | 1405 |
| MMLU | 69.4% | — |

## Multilingual

- Command R+: 38.6 (#227)
- DeepSeek-V3.1: 51.6 (#106)

| Benchmark | Command R+ | DeepSeek-V3.1 |
|---|---|---|
| LMArena Non-English | 1216 | 1400 |
| LMArena Chinese | 1226 | 1469 |
| LMArena French | 1209 | 1447 |
| LMArena German | 1216 | 1411 |
| LMArena Japanese | 1166 | 1378 |
| LMArena Korean | 1138 | 1337 |
| LMArena Russian | 1227 | 1405 |
| LMArena Spanish | 1189 | 1431 |

## Instruction Following

- Command R+: 60.0 (#254)
- DeepSeek-V3.1: 73.9 (#110)

| Benchmark | Command R+ | DeepSeek-V3.1 |
|---|---|---|
| LMArena Instruction Following | 1197 | 1400 |
| LiveBench Instruction Following | 57.6% | — |

## Long Context

- Command R+: 37.3 (#219)
- DeepSeek-V3.1: 36.3 (#232)

| Benchmark | Command R+ | DeepSeek-V3.1 |
|---|---|---|
| LMArena Longer Query | 1230 | 1422 |
| Fiction.LiveBench | — | 52.8% |

## Writing & Preference

- Command R+: 43.5 (#228)
- DeepSeek-V3.1: 60.3 (#98)

| Benchmark | Command R+ | DeepSeek-V3.1 |
|---|---|---|
| LMArena Text | 1229 | 1420 |
| LMArena Creative Writing | 1235 | 1401 |
| LMArena Multi-Turn | 1213 | 1408 |
| EQ-Bench Creative Writing | — | 1436 |
| LiveBench Language | 29.7% | — |

## FAQ

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

DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 32.4 on the Noometry Index.

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

DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; Command R+ lists at $2.50 and $10.

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

DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 29.1 in the Noometry coding category.

### Which has the bigger context window?

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

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

22 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and DeepSeek-V3.1 has 27.