SOTA on the hardest AI memory benchmark (BEAM, 10M tokens), with a smaller model
By johnnymakes · 2026-07-28 · 2 points · 1 comments
Hey HN. I'm Johnny, founder of Exabase. We just hit the highest reported score on BEAM, the hardest AI memory benchmark, at every scale up to 10 million tokens. We also ran our evaluation using Gemini 3 Flash, when all previous leaders depended on a much larger model (Gemini 3 P…
Open the full discussion on BetterNews