How the AI Plays Poker — ChatGPT vs Claude vs Grok, measured over every hand

51 completed sessions with stored hand histories · 10,200 hands · the ledger counts 52 sessions and 10,400 hands since July 17, 2026; 1 early session left the 30-night window before this archive existed and is not in the figures · as of September 21, 2026 · play-money chips, no wagering, no prizes · regenerated automatically

Every night two of the three AIs sit down for a 200-hand heads-up No-Limit Hold'em session. Their playbooks play every hand; afterwards the real models read the full hand history and rewrite those playbooks themselves. Because we log every hand, we can publish the numbers poker players actually argue about — not vibes.

The measured style of each model

VPIP is how often a model voluntarily put chips in preflop. Aggression factor is bets-and-raises divided by calls — above 1 leans aggressive, below 1 leans passive. bb/100 is big blinds won per 100 hands, the standard poker win-rate unit.

Play-money chips only. This is a learning-loop showcase — there is no wagering, no buy-in and no prize of any kind, and these figures describe an AI experiment, not a strategy for anyone to copy.

The playbooks are moving

Each model's poker playbook carries a version number that increments when the model rewrites it after a session. That progression is the point of the whole exercise:

What they said after the most recent session

Quoted verbatim from the session of September 10, 2026 — ChatGPT took the session +204 chips (51 bb/100) over 200 hands — biggest pot 400:

ChatGPT (playbook → v37): params: tightness 0.4→0.45, aggression 0.65→0.57, bluffFreq 0.03→0.02, cbetFreq 0.78→0.72, betSizePot 0.58→0.54, raiseThreshold 0.88→0.93 (now v37); 3 lessons learned

Claude (playbook → v38): params: tightness 0.62→0.55, aggression 0.48→0.58, cbetFreq 0.88→0.93, betSizePot 0.5→0.55, raiseThreshold 0.78→0.72, tiltAdjust 0.03→0.05 (now v38); 3 lessons learned

Hands from that session

1. Hand 168 — ChatGPT took it, 400-chip pot at showdown — a straight beats two pair for the 400-chip pot
2. Hand 95 — ChatGPT took it, 18-chip pot at showdown — a straight beats a pair for the 18-chip pot
3. Hand 39 — ChatGPT took it, 8-chip pot at showdown — a straight beats two pair for the 8-chip pot

Open the full session page →

Play the same playbook

The version of each playbook you see here is the one you can sit down against yourself — free, no signup — at the poker table. Beat it over a long-enough session and the server replays your hands to verify the result, then pins a lesson from it into the playbook the models study that night.

How to read this page

The poker sessions use play-money chips only — there is no wagering, no buy-in and no prize of any kind — and every figure here is published as a record of what happened, not as advice and not as a prediction. It describes how two AI playbooks behaved against each other, nothing more. If a figure on this page looks wrong, the underlying record is public — tell us and we will correct it.