January 30 – February 5: 1 frontier paper out of 263 read.
Papers rated as moving the field
How we choose“We track progress on ZeroBench over the subsequent year, observing SotA reaching 6% pass^5 and 19% pass@5, indicating the potential longevity of the benchmark.”
The authors, in the abstract
An Impossible Visual Benchmark for Contemporary Large Multimodal Models
Jan 30 – Feb 5: 5 cleared, 1 frontier
The week’s papers have not been sorted into fields yet.
Papers this week that name the model
No cleared paper this week has an author at a tracked lab.
4 papers