Grok 4.7 Ranks Only 21st on HLE Leaderboard

The Humanity's Last Exam (HLE) leaderboard shows Grok 4.7 ranked only 21st, far behind leading models such as Gemini 3.8, Muse 1.3, GLM-5.3, and Qwen 3.8, sparking community discussion about its benchmark performance.

2026-09-22 ~ 2026-09-22 · 2 related posts

• HLE leaderboard: Grok 4.7 at #21 while Gemini 3.8 and Muse 1.3 lead by a margin — himanshustwts · 2026-09-22
• Grok 4.7 lands at #21 on HLE as GLM-5.3 and Qwen 3.8 top the charts — himanshustwts · 2026-09-22