We're thrilled to unveil AReaL v0.2 boba! #LRM #AI
✅ SOTA 7B model: 61.9 AIME24 & 48.3 AIME25
✅ 32B model: match QwQ on AIME24 with only 200 samples!
✅ Full #SGLang support
Training data/weights ALL OPENSOURCE🔥🔥🔥 Like A ReaL boba, for everyone! 🧋https://t.co/OopXbE7sTJ https://t.co/rEn9g7sJLS
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
Why it matters
open weightsA model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.Full definition → plus the training data behind them, with AIME scores to verify, make this an RL recipe you can reproduce instead of only reading about.
