Comment by dannyw
14 hours ago
From my rough recollection, all 3 of the past updates all had the effects of decreasing the score of open weight models.
One was rushed and same-day updated as GLM 5.3 (iirc) got added; of course its main change to rankings was lower GLM scores.
I think refer to Qwen 3.8 Max.
It was released, got the top agantic ranking, and AA immediately made an update to their index calculation that made it lose the top spot. It was very suspicious.
https://news.ycombinator.com/item?id=49201726
Such releases often show weaknesses if the intelligence index, because the models that are ranked jointly do not have the same percieved level of quality.
So instead of the narrative of benchmaxing, in truth it's benchminimizing of competitors by the U.S. oligarchy?