KradleBench pits humans and AI in live multi-agent Minecraft evals
lmoroney · x · 2026-11-19
Kradle AI introduced KradleBench, a new benchmark running evals in live, multi-agent worlds. The premise: existing benchmarks are saturated and can't tell how close we are to AGI or what models still need to learn, so both AIs and humans should be evaluated in dynamic environments.
Minecraft legend @SethBling represented humanity and held #1 until GPT 6.2 Astra unseated him the day after its launch. KradleBench will soon open to all humans and all models.
More from Models
- Physician: AI competition now measured in weeks, GPT-6 versions 7 days apart — ramos_casals · 2026-11-19
- Tipster claims Google's 'Gemini Neon' is live, official post within 30 minutes — imjustnewatai · 2026-11-19
- micro1's flow qc model screens training data for benchmark leaks before release — Exp_Mark · 2026-11-19
- Gemini 4 Neon appears: frontier intelligence at $3/$15 per M tokens — Angaisb_ · 2026-11-19
- Leaker predicts new DeepSeek paper this week, scheduled for November 11 — teortaxesTex · 2026-11-19
- Gemini 4 Neon rollout begins: leaked UI shows 3-tier Gemini 4 lineup with Carbon locked — testingcatalog · 2026-11-19