# Command R+ vs DeepSeek-R1-Distill-Llama-70B

> DeepSeek-R1-Distill-Llama-70B is the stronger model overall, scoring 37.4 to 32.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/command-r-plus-vs-deepseek-r1-distill-llama-70b
- Last updated: 2026-10-10
- Shared benchmarks: 9

## Summary

- They share 9 benchmarks with published results for both. Command R+ scores higher in 1 category and DeepSeek-R1-Distill-Llama-70B in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek-R1-Distill-Llama-70B leads 24.1 to 8.9.
- The biggest single-benchmark swing is LiveBench Reasoning: 24.8% for Command R+ and 67.6% for DeepSeek-R1-Distill-Llama-70B.

## Snapshot

| | Command R+ | DeepSeek-R1-Distill-Llama-70B |
|---|---|---|
| Provider | Cohere | DeepSeek |
| Noometry Index | 32.0 | 37.4 |
| Rank | 251 | 187 |
| Context | 128K | — |
| Input $/M | $2.50 | — |
| Output $/M | $10 | — |
| Weights | Open | Open |

## Coding

- Command R+: 28.6 (#304)
- DeepSeek-R1-Distill-Llama-70B: 36.3 (#197)

| Benchmark | Command R+ | DeepSeek-R1-Distill-Llama-70B |
|---|---|---|
| BigCodeBench Instruct | 33.8% | 35.3% |
| LiveBench Coding | 19.1% | 51.6% |
| BigCodeBench Complete | 41.9% | 49.9% |
| LMArena Coding | 1187 | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |

## Reasoning

- Command R+: 8.9 (#341)
- DeepSeek-R1-Distill-Llama-70B: 24.1 (#150)

| Benchmark | Command R+ | DeepSeek-R1-Distill-Llama-70B |
|---|---|---|
| LiveBench Reasoning | 24.8% | 67.6% |
| LiveBench Data Analysis | 38.1% | 55.9% |
| LiveBench | 31.8% | 54.5% |
| SimpleBench | 17.4% | — |
| Kagi LLM Benchmark | — | 52.3% |
| LMArena Hard Prompts | 1186 | — |
| DTBench | 54.9% | — |
| LMCA | 5% | — |
| Epoch Capabilities Index | 119.28 | — |

## Math

- Command R+: 26.6 (#239)
- DeepSeek-R1-Distill-Llama-70B: 34.3 (#161)

| Benchmark | Command R+ | DeepSeek-R1-Distill-Llama-70B |
|---|---|---|
| LiveBench Math | 21.3% | 58.1% |
| OTIS Mock AIME 2024-2025 | — | 51.4% |
| LMArena Math | 1188 | — |
| MATH Level 5 | — | 89.9% |

## Knowledge

- Command R+: 35.9 (#165)
- DeepSeek-R1-Distill-Llama-70B: 30.7 (#216)

| Benchmark | Command R+ | DeepSeek-R1-Distill-Llama-70B |
|---|---|---|
| GPQA Diamond | — | 55.7% |
| Vectara Hallucination Rate | 6.9% | — |
| LMArena Expert | 1174 | — |
| MMLU | 69.4% | — |

## Multilingual

- Command R+: 38.8 (#222)
- DeepSeek-R1-Distill-Llama-70B: —

| Benchmark | Command R+ | DeepSeek-R1-Distill-Llama-70B |
|---|---|---|
| LMArena Non-English | 1216 | — |
| LMArena Chinese | 1226 | — |
| LMArena French | 1208 | — |
| LMArena German | 1216 | — |
| LMArena Japanese | 1166 | — |
| LMArena Korean | 1138 | — |
| LMArena Russian | 1227 | — |
| LMArena Spanish | 1189 | — |

## Instruction Following

- Command R+: 60.2 (#249)
- DeepSeek-R1-Distill-Llama-70B: 68.3 (#185)

| Benchmark | Command R+ | DeepSeek-R1-Distill-Llama-70B |
|---|---|---|
| LiveBench Instruction Following | 57.6% | 69.9% |
| LMArena Instruction Following | 1197 | — |

## Long Context

- Command R+: 37.3 (#214)
- DeepSeek-R1-Distill-Llama-70B: —

| Benchmark | Command R+ | DeepSeek-R1-Distill-Llama-70B |
|---|---|---|
| LMArena Longer Query | 1231 | — |

## Writing & Preference

- Command R+: 43.7 (#223)
- DeepSeek-R1-Distill-Llama-70B: 49.0 (#189)

| Benchmark | Command R+ | DeepSeek-R1-Distill-Llama-70B |
|---|---|---|
| LiveBench Language | 29.7% | 23.8% |
| LMArena Text | 1229 | — |
| LMArena Creative Writing | 1235 | — |
| LMArena Multi-Turn | 1213 | — |

## FAQ

### Is Command R+ better than DeepSeek-R1-Distill-Llama-70B?

DeepSeek-R1-Distill-Llama-70B is the stronger model overall, scoring 37.4 to 32.0 on the Noometry Index.

### Is Command R+ or DeepSeek-R1-Distill-Llama-70B better for coding?

DeepSeek-R1-Distill-Llama-70B scores higher on coding benchmarks: 36.3 versus 28.6 in the Noometry coding category.

### How many benchmarks do Command R+ and DeepSeek-R1-Distill-Llama-70B share?

9 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and DeepSeek-R1-Distill-Llama-70B has 13.