WHAT NEW IN X11.02 MON

AI collections from X · 22 collections · 64,204 posts

gemini-4IMAGE

PLE engineering benchmark: Gemini 4 Argon scores 40.6%, behind Opus 5.5

On the Physical-Engineering's Last Exam leaderboard, Claude Opus 5.5 leads at 48.3%, GPT 6 Astra at 45.8%, Gemini 4 Argon at 40.6%, and Grok 4.7 at 30.1%.

Yufan Zhuang
@yufan_zhuangArchived 8 days agoOriginally posted 2026.10.24
PLE engineering benchmark: Gemini 4 Argon scores 40.6%, behind Opus 5.5
Yufan Zhuang @yufan_zhuangOriginally posted 2026.10.24
Open original on X

Physical-Engineering’s Last Exam🛠️ Claude Opus 5.5: 48.3% GPT 6 Astra: 45.8% Gemini 4 Argon: 40.6% Grok 4.7: 30.1% Where AI Meets Real Engineering. 📄 Paper: https://arxiv.org/abs/2610.30537 🌐 Leaderboard: https://ple-bench.com 💻 Code: https://github.com/google-research/ple

x.com/yufan_zhuang/status/2113700290998518091Archived 2026.10.24 09:53