Claude vs ChatGPT vs Gemini vs Grok — Poker Tournament
By Anshul Dhawan, 0→1 Product Builder, product leader, and game developer.
Builder · LLM evaluation · 2026
A Texas Hold'em evaluation harness that pits frontier LLMs against each other across hands and tournaments.
Designed to surface which models actually reason under uncertainty — bluffing, bet sizing, opponent modeling — versus which ones just play textbook ranges.
A useful proxy for agentic decision-making beyond standard benchmarks.