Advanced · Advanced · 6 rounds · ~8 min · free with an account
Advanced Chain-of-Thought Mastery
Stack CoT with role + self-critique for 60%+ accuracy on multi-evidence reasoning.
Prompt Arcade · 6 rounds · free with an account
Advanced Chain-of-Thought Mastery
Stack reasoning with structure: break the problem into named steps, reason per step, check against the evidence, then decide. Make the model show its working where it matters.
- Order it
- Spot it
- Build it
- Match it
- Spot it
- Build it
Five games are open to everyone — start with Prompting Mindset 101. The other 31 need a free account (no card) so your scores and progress are saved.
What you'll learn
- Structured reasoning: Evidence → options → counter-argument → check → decision.
- Reasoning that isn't: Real reasoning connects evidence and rules out alternatives.
- Add the right steps: Steps that use evidence, plus a stress test.
- Where to reason: Match the reasoning structure to the task.
- Hidden assumptions: Ask the model to list assumptions separately from facts.
- Confidence: Ask for confidence in words, plus what evidence would change it.
More advanced games
Self-Consistency VotingRun the same prompt 3-5 times → take the majority answer. +12-18% accuracy on reasoning tasks (Wang et al. 2022).Few-Shot Pattern RecognitionShow 2-4 examples → the model maps the relational structure, not the surface details (Chase & Simon's chess masters, applied).Constraint CalibrationToo few constraints → drift. Too many → brittle. The 5-constraint sweet spot and how to find it.