Mistral

Mistral Small (Sep '24)

Sep 17, 2024Open weightsHugging Face

Compare

Intelligence

5.8

#647 of 744Rank 647 of 744 measured models

Output speed

154 t/s

#80 of 403Rank 80 of 403 measured models

Price/1M

$0.30

#206 of 659Rank 206 of 659 measured models

Context window

33K

#1012 of 1199Rank 1012 of 1199 measured models

Mistral Small (Sep '24) scores 5.8 on the Artificial Analysis Intelligence Index, ranking 647th of 744 measured models. The closest models on this index are Gemini 1.0 Ultra (5.8), Mistral Large (Feb '24) (5.8), and NVIDIA Nemotron Nano 12B v2 VL (5.8). At $0.30 per million tokens (3:1 input/output blended price), it is cheaper than Mistral Large (Feb '24) ($6), priced close to NVIDIA Nemotron Nano 12B v2 VL ($0.30). With an output speed of 154 t/s, it is slower than NVIDIA Nemotron Nano 12B v2 VL (206 t/s).