This Thanksgiving period will be a cambrian explosion of capable models.
Glm 5.5 I bet, but still too early to tell
[flagged]
"Random AI lab makes up a new benchmark that puts at least one of its models ahead of Fable 5.2"
It is interesting that the Kimi model gets a very high “slop score” but “professional critiques” gave it a pretty high score. Do critiques have no taste or the “slop” is not slop anymore?
Saying this when none of the gallery examples show the new model's output is the ultimate "trust me, bro" move.
Deepseek V5 trained on Huawei Ascend?