in the loop

Mistral Large
#192 of 274 scored.

MistralFeb 26, 2024Closed

Capabilities Index

Range 114.4–125.1

122.0

Context

Takes text, file

128K

Input

Per 1M tokens

$2.00

Output

Per 1M tokens

$6.00

Benchmarks

How it scores.

  • GPQA Diamond18.4%

    160th of 186

  • Mock AIME1.8%

    163rd of 176

Everything else Epoch has for it

  • MMLU58.4%
  • DTBench26.5%
  • MATH level 524.5%

On the index

Around it.

  1. #189Gemini 1.5 Flash (May 2024)Google122.6
  2. #190Gemma 2 27BGoogle · $0.65 in122.1
  3. #191Mixtral 8x22BMistral122.0
  4. #192Mistral LargeMistral · $2.00 in122.0
  5. #193phi-3-small 7.4BMicrosoft121.8
  6. #194phi-3-medium 14BMicrosoft121.2
  7. #195Claude 3 SonnetAnthropic120.7

Sources