Local
Istanbul-based team matches frontier AI labs on knowledge-work benchmark at a fraction of the cost
Meet in Common connects news with real conversations. Use ThinkMatch to arrange a Roundtable and meet people to discuss this story.
Source: The Waxahachie Sun

Loxi scored 58.2% on JobBench, matching Claude Fable 5 and finishing ahead of several frontier models while completing all 65 tasks at under a tenth of the cost of the largest models on the leaderboard.
This excerpt comes from the named source. Read the original for the full reporting.
Read the original at The Waxahachie Sun


