in the loop

Mistral Large 2 (Nov 2024)
#168 of 274 scored.

MistralNov 18, 2024Open weights

Capabilities Index

Range 122.7–130.6

128.5

Context

Tokens

—

Input

Per 1M tokens

—

Output

Per 1M tokens

—

Benchmarks

How it scores.

  • GPQA Diamond35.1%

    131st of 186

  • Mock AIME7.7%

    139th of 176

Everything else Epoch has for it

  • MATH level 550.3%
  • DTBench34.7%
  • FrontierMath-2025-02-28-Private0.6%

On the index

Around it.

  1. #165GPT-4o (Nov 2024)OpenAI128.8
  2. #166GPT-4o (Aug 2024)OpenAI128.8
  3. #167Llama 3.1-405BMeta128.8
  4. #168Mistral Large 2 (Nov 2024)Mistral128.5
  5. #169Qwen2.5-32BAlibaba128.5
  6. #170Mistral Large 2 (Jul 2024)Mistral127.5
  7. #171Mistral Small 3.1Mistral127.5

Sources