MiMo-V2.6-Pro

Xiaomi · Huge open-weight models. Anyone can download them and run them on their own racks.

D3 · Open Giantepic

Intelligence ▲ higher wins
Intelligence Index: a composite score from 10 hard evaluations covering reasoning, knowledge, coding, agents and science.
46.3
beats 77% of deck
Hallucination ▼ lower wins
Hallucination rate: of the questions a model gets wrong, how often it confidently makes up an answer instead of saying it doesn't know. Lower wins.
41 %
beats 68% of deck
Context ▲ higher wins
Context window: how many tokens of input the model can consider at once.
1M
beats 65% of deck
Knowledge ▲ higher wins
Training-data cutoff: the most recent month the model learned about. Later wins. N/D means the lab hasn't disclosed it, and an N/D card loses this stat.
N/D
beats 16% of deck
Speed ▲ higher wins
Median output speed in tokens per second, measured on the labs' own APIs.
43 tok/s
beats 10% of deck
Response ▼ lower wins
End-to-end response time: seconds to receive a 500-token answer, thinking time included. Lower wins.
62.9 s
beats 42% of deck
Price ▼ lower wins
Blended price per million tokens (3:1 input to output). Lower wins.
$0.54
beats 65% of deck
Modalities ▲ higher wins
Number of supported input and output modalities: text, image, audio and video.
5
beats 95% of deck

Knowledge: The lab hasn’t published a training-data cutoff, so this card shows N/D and loses the Knowledge stat.