# Command R+ vs Llama 3-8B

> Command R+ is the stronger model overall, scoring 32.0 to 25.3 on the Noometry Index. Llama 3-8B costs 31× less per token, which makes it the better buy when Command R+'s lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/command-r-plus-vs-llama-3-8b
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Command R+ scores higher in 6 categories and Llama 3-8B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Command R+ leads 35.9 to 7.8.
- The biggest single-benchmark swing is DTBench: 54.9% for Command R+ and 43.9% for Llama 3-8B.
- Llama 3-8B is cheaper at $0.14 / $0.14 per million input/output tokens, against $2.50 / $10 for Command R+.
- Command R+ accepts more context: 128K tokens versus 8K.

## Snapshot

| | Command R+ | Llama 3-8B |
|---|---|---|
| Provider | Cohere | Meta |
| Noometry Index | 32.0 | 25.3 |
| Rank | 251 | 338 |
| Context | 128K | 8K |
| Input $/M | $2.50 | $0.14 |
| Output $/M | $10 | $0.14 |
| Weights | Open | Open |

## Coding

- Command R+: 28.6 (#304)
- Llama 3-8B: 30.5 (#285)

| Benchmark | Command R+ | Llama 3-8B |
|---|---|---|
| BigCodeBench Instruct | 33.8% | 31.9% |
| LMArena Coding | 1187 | 1152 |
| BigCodeBench Complete | 41.9% | 36.9% |
| HumanEval+ | 56.7% | 56.7% |
| MBPP+ | 63.5% | 54.8% |
| LiveBench Coding | 19.1% | — |

## Reasoning

- Command R+: 8.9 (#341)
- Llama 3-8B: 13.8 (#321)

| Benchmark | Command R+ | Llama 3-8B |
|---|---|---|
| LMArena Hard Prompts | 1186 | 1133 |
| DTBench | 54.9% | 43.9% |
| Epoch Capabilities Index | 119.28 | 116.33 |
| SimpleBench | 17.4% | — |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | 24.8% | — |
| LiveBench Data Analysis | 38.1% | — |
| LMCA | 5% | — |
| Adversarial NLI | — | 57.3% |
| ForecastBench | — | 58.6 |
| LiveBench | 31.8% | — |
| WinoGrande | — | 75.7% |

## Math

- Command R+: 26.6 (#239)
- Llama 3-8B: 8.3 (#317)

| Benchmark | Command R+ | Llama 3-8B |
|---|---|---|
| LMArena Math | 1188 | 1151 |
| OTIS Mock AIME 2024-2025 | — | 1.9% |
| LiveBench Math | 21.3% | — |
| MATH Level 5 | — | 6.1% |

## Knowledge

- Command R+: 35.9 (#165)
- Llama 3-8B: 7.8 (#303)

| Benchmark | Command R+ | Llama 3-8B |
|---|---|---|
| LMArena Expert | 1174 | 1113 |
| MMLU | 69.4% | 68.8% |
| GPQA Diamond | — | 26.1% |
| Vectara Hallucination Rate | 6.9% | — |
| ARC (AI2) Challenge | — | 82.8% |
| OpenBookQA | — | 82.6% |
| TriviaQA | — | 67.7% |

## Multilingual

- Command R+: 38.8 (#222)
- Llama 3-8B: 31.0 (#256)

| Benchmark | Command R+ | Llama 3-8B |
|---|---|---|
| LMArena Non-English | 1216 | 1098 |
| LMArena Chinese | 1226 | 1076 |
| LMArena French | 1208 | 1158 |
| LMArena German | 1216 | 1104 |
| LMArena Japanese | 1166 | 967 |
| LMArena Korean | 1138 | 1003 |
| LMArena Russian | 1227 | 1109 |
| LMArena Spanish | 1189 | 1172 |

## Instruction Following

- Command R+: 60.2 (#249)
- Llama 3-8B: 58.7 (#255)

| Benchmark | Command R+ | Llama 3-8B |
|---|---|---|
| LMArena Instruction Following | 1197 | 1127 |
| LiveBench Instruction Following | 57.6% | — |

## Long Context

- Command R+: 37.3 (#214)
- Llama 3-8B: 34.2 (#246)

| Benchmark | Command R+ | Llama 3-8B |
|---|---|---|
| LMArena Longer Query | 1231 | 1128 |

## Writing & Preference

- Command R+: 43.7 (#223)
- Llama 3-8B: 37.7 (#251)

| Benchmark | Command R+ | Llama 3-8B |
|---|---|---|
| LMArena Text | 1229 | 1166 |
| LMArena Creative Writing | 1235 | 1150 |
| LMArena Multi-Turn | 1213 | 1152 |
| LiveBench Language | 29.7% | — |

## FAQ

### Is Command R+ better than Llama 3-8B?

Command R+ is the stronger model overall, scoring 32.0 to 25.3 on the Noometry Index. Llama 3-8B costs 31× less per token, which makes it the better buy when Command R+'s lead doesn't matter for your workload.

### Which is cheaper, Command R+ or Llama 3-8B?

Llama 3-8B is cheaper. It lists at $0.14 per million input tokens and $0.14 per million output tokens; Command R+ lists at $2.50 and $10.

### Is Command R+ or Llama 3-8B better for coding?

Llama 3-8B scores higher on coding benchmarks: 30.5 versus 28.6 in the Noometry coding category.

### Which has the bigger context window?

Command R+ does, with 128K tokens against 8K.

### How many benchmarks do Command R+ and Llama 3-8B share?

24 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Llama 3-8B has 34.