in the loop

Magistral Small 1.0
#149 of 274 scored.

MistralJun 10, 2025Open weights

Capabilities Index

Range 128.8–134.5

133.2

Context

Tokens

—

Input

Per 1M tokens

—

Output

Per 1M tokens

—

Benchmarks

How it scores.

  • GPQA Diamond41.4%

    124th of 186

  • ARC-AGI-20.0%

    72nd of 79

  • Mock AIME29.9%

    123rd of 176

Everything else Epoch has for it

  • ARC-AGI5.0%

On the index

Around it.

  1. #146Mistral Medium 3Mistral · $0.40 in134.1
  2. #147Gemini 2.5 Flash-Lite (Jun 2025)Google133.9
  3. #148Claude 3.5 Sonnet (October 2024)Anthropic133.6
  4. #149Magistral Small 1.0Mistral133.2
  5. #150Qwen2.5-MaxAlibaba132.5
  6. #151DeepSeek-V3DeepSeek · $0.32 in132.3
  7. #152Llama 4 MaverickMeta · $0.19 in132.2

Sources