in the loop

Mistral Small 3.1
#171 of 274 scored.

MistralMar 17, 2025Open weights

Capabilities Index

Range 122.2–129.3

127.5

Context

Tokens

—

Input

Per 1M tokens

—

Output

Per 1M tokens

—

Benchmarks

How it scores.

  • GPQA Diamond30.0%

    143rd of 186

  • Mock AIME5.7%

    151st of 176

Everything else Epoch has for it

  • MATH level 546.8%
  • DTBench31.1%
  • Chess Puzzles0.0%

On the index

Around it.

  1. #168Mistral Large 2 (Nov 2024)Mistral128.5
  2. #169Qwen2.5-32BAlibaba128.5
  3. #170Mistral Large 2 (Jul 2024)Mistral127.5
  4. #171Mistral Small 3.1Mistral127.5
  5. #172Llama 3.3 70BMeta127.3
  6. #173GPT-4 Turbo (Apr 2024)OpenAI127.3
  7. #174Claude 3.5 HaikuAnthropic127.2

Sources