Hacker News new | ask | show | jobs
by cbg0 503 days ago
Even the full model scores below Claude on livebench so a distilled version will likely be even worse.
1 comments
rsanek 503 days ago
Based on the leaderboard R1 is significantly better than Claude? https://livebench.ai/#/
link
cbg0 503 days ago
Not at coding.
link