X · @teortaxesTex
· X / Twitter
Interesting how *uneven* the perf of open models, and particularly V4, is. On one task it's the best in class; on another, bottom of the barrel. Patch…
Interesting how *uneven* the perf of open models, and particularly V4, is. On one task it's the best in class; on another, bottom of the barrel. Patchy coverage.The strongest models, however, are crushingly consistent.Artificial Analysis: Introducing six new Artificial Analysis Capability Indices for comparing model ca