AA-PersonalityBench Humor Elo Ranking: Gemini 4.1 Arvon Tops the Chart

Artificial Analysis released an AA-PersonalityBench humor Elo ranking based on LLM-judge pairwise comparisons over 30 prompts, with Gemini 4.1 Arvon leading by a wide margin while a GPT Turbo model landed at the bottom with around 179 Elo.

2026-10-20 ~ 2026-10-21 · 2 related posts

• Humor Elo Leaderboard: Gemini Crushes Rivals While GPT-3.5 Turbo Tanks at 179 — opmgyhx · 2026-10-20
• Humor Elo leaderboard: Gemini 4.1 Arvon tops at 1573, GPT-5.1 Turbo last with 179 — jon_barron · 2026-10-21