OpenAI's unreleased model ExploitGym evaluation

Update 1 sa 1PinakabagoNob 13, 4:11 PM UTCAraw 1

OpenAI previews a 77% exploit score—but leaves the comparison unproven

The unnamed model reportedly leads GPT-6 Cyber by 24.4 percentage points on ExploitGym. Missing test conditions and access rules limit what that result tells defenders.

Manood

Pinakamaagang sourceギズモード・ジャパンNob 12, 10:00 PM UTC

Ano ang una nating nalaman

• 77.0%Unreleased model’s reported ExploitGym score
• 52.6%GPT-6 Cyber’s reported ExploitGym score
• ~38%Mythos 5.2’s spoken reference score