XXO Bench creator claims three-year undefeated streak against AI models

The self-described "XXO Bench" creator says no AI model has beaten the benchmark in three years, adding that "pleasing models are a problem."
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Post-training course materials invite educator feedback
- Kimi K3 available to try free on Together Chat
- Rhodium's Goujon urges holistic AI safety approach
- Cheap AI intelligence revives graph knowledge and ontologies
- US will exempt Chinese open-weight models from safety testing requirements