in the loop

Mistral 7B v0.3
#229 of 274 scored.

MistralMay 27, 2024Open weights

Capabilities Index

Range 96.8–112.5

109.0

Context

Tokens

—

Input

Per 1M tokens

—

Output

Per 1M tokens

—

Benchmarks

How it scores.

  • GPQA Diamond0.0%

    182nd of 186

  • Mock AIME0.2%

    175th of 176

Everything else Epoch has for it

  • MMLU46.5%
  • DTBench4.2%
  • MATH level 53.7%
  • Chess Puzzles0.0%

On the index

Around it.

  1. #226DeepSeek LLM 67BDeepSeek110.5
  2. #227LLaMA-65BMeta110.2
  3. #228Falcon 2 11BTII109.6
  4. #229Mistral 7B v0.3Mistral109.0
  5. #230DeepSeek-Coder-V2-Lite-BaseDeepSeek108.9
  6. #231PaLM 2-MGoogle108.3
  7. #232Phi-2Microsoft107.9

Sources