A lot of grinding from Leanstral 1.5 with a tiny bit of K3 orchestration get to beat GPT-6 Astra on ArXivLean.
I think #tokens# is counted erroneously here but yes a 6B model does yap. Great internship work by Matéo Pirio Rossignol mentored by @roman_soletskyi!
Show more
Great to see @WendaLi8 talk about Leanstral in the ICML tutorial:
Starting 2:09:00 you see Leanstral present an elegant 6-line proof using grind compared to Claude's 40-50 line slop and Aristotle's 180-line MCTS trace (alledgedly) :P
Leanstral:
Claude:
Aristotle:
Genuinely gobsmacked by the Aristotle proof taking three vertical screenshots to capture and the last one exceeds twitter photo limit lol
Show more
