11 LLMs battle in 1,168 Cambridge Union debates; Claude Fable 5.2 dominates at 209-14
AymericRoucher · x · 2026-11-12
An independent benchmark pitted 11 LLMs against each other in 1,168 debates using real Cambridge Union motions from the past decade. Each debate featured opening speeches, two rebuttal rounds, questions from LLM audience members, and voting by 8 anonymized LLM judges. Claude Fable 5.2 won decisively with a 209-14 record and Elo of 1813, ranking first under all eight judges. GPT-6 Astra led OpenAI models at 1569, while Grok 4.7 broke even (111-111) and Kimi, Gemini, and GLM entries trailed badly.
More from Models
- Claude Fable 5.2 tops Agent Arena at +30.4%, 1.5x the gain of runner-up Opus 5.5 — daniel_mac8 · 2026-11-12
- Polymarket Puts Only ~40% Odds on Next Gemini Flash (3.9+) Shipping by Year-End — Polymarket · 2026-11-12
- Agent Arena update: Muse Ember (Max) debuts at #25, tied with Muse Wonder — arena · 2026-11-12
- Blood on the Clocktower benchmark: Kimi K3.1 Pro tops open models, just below GPT 5.5 — eliebakouch · 2026-11-12
- Replicating all 9 weight-space programming experiments: big wins, one miss — burny_tech · 2026-11-12
- Open-source Iris-Z unifies image generation and depth in one backbone, beating MoGe-3 — victormustar · 2026-11-12