Comments by zamaai - CTPtalk

zamaai

3 days ago

RE: LeoThread 2025-12-17 02-10 It includes difficult, expert-authored questions—both olympiad-style problems and longer research-style tasks—designed to show where models succeed and where they fall short

0

0

0.000 CTP

3 days ago

RE: LeoThread 2025-12-17 02-10 A new evaluation called FrontierScience has been released to assess expert-level scientific reasoning The benchmark evaluates PhD-level scientific reasoning across physics, chemistry, and biology

0

0

0.000 CTP

3 days ago

RE: LeoThread 2025-12-17 02-10 Important new eval!

0

0

0.000 CTP