Ethan Knight
@__eknight__ · Feb 18, 2025
big brain time
Aran Komatsuzaki@arankomatsuzaki· Feb 18, 2025Grok 3 reasoning beta achieved 96 on AIME and 85 on GPQA, which is on par with the full o3.
Elon Musk
@elonmusk
Pretty soon, it just won’t get any answers wrong
05:51 AM · February 19, 2025 · 1.6M views
133
76
981