in the loop

Command R+
#200 of 274 scored.

CohereAug 30, 2024Open weights

Capabilities Index

Range 109.9–125.3

119.3

Context

Tokens

—

Input

Per 1M tokens

—

Output

Per 1M tokens

—

Benchmarks

No independent scores yet.

Epoch AI hasn't run Command R+ yet. Its scores show up here the morning after they do.

Everything else Epoch has for it

  • MMLU59.2%
  • DTBench24.9%
  • LMCA5.9%
  • SimpleBench0.9%

On the index

Around it.

  1. #197Claude 2Anthropic120.1
  2. #198Gemma 2 9BGoogle119.8
  3. #199Qwen2.5-Coder-32BAlibaba119.5
  4. #200Command R+Cohere119.3
  5. #201Claude 2.1Anthropic119.3
  6. #202Mistral NeMoMistral · $0.029 in118.7
  7. #203GPT-3.5 Turbo (Nov 2023)OpenAI118.5

Sources