What is GTO poker?

GTO — short for game theory optimal — is the term poker players use for the unexploitable equilibrium strategy in a given spot. It comes from the mathematics of two-player zero-sum games, where a Nash equilibrium is a pair of strategies (one for each player) such that neither player can improve their expected value by unilaterally changing their own strategy.

The practical meaning for a poker player: a GTO strategy can be played in every spot without ever losing money to an opponent who's also playing optimally. It's a defensive baseline. Notably, it is not the strategy that maximizes profit against weak opponents — that's an "exploitative" strategy, and it's usually different from GTO.

How solvers compute GTO

Modern poker solvers use a family of algorithms called Counterfactual Regret Minimization (CFR). The intuition: start with both players playing arbitrary strategies; repeatedly let each player look back at every action they took and see if they would have profited by playing a different action; nudge their strategy slightly toward whichever action was best in hindsight. Iterate millions of times, and the strategy converges to an approximate Nash equilibrium.

For preflop, this calculation is tractable — the game tree is small enough that solvers can compute equilibria within hours on a single machine. For postflop, the tree explodes exponentially with each street, requiring abstraction techniques (bucketing similar hands together) and dedicated solver software. Tools like PioSOLVER, GTO+, and our own in-browser Monte Carlo estimator all attempt this with different speed/accuracy tradeoffs.

Why GTO is not always the goal

The dirty secret of GTO study is that almost no one you'll ever play against is playing GTO. They have leaks — they fold too much, call too much, never bluff, never fold a top pair. Against these opponents, the maximum-EV strategy is not GTO; it's an exploit that targets their specific leaks.

The reason GTO matters anyway: it's the baseline from which you can identify and exploit leaks. Knowing the GTO defending frequency for big blind versus a button open (~52%) lets you immediately spot that the player who folds 70% is over-folding, and adjust by stealing more aggressively. Without the GTO baseline, you can't tell whether someone's actually leaking or just playing in a way you don't understand.

When to study GTO vs. exploits

A rough rule: study GTO for the spots that repeat constantly (preflop opens, single-raised pot c-bets, common board textures) because these are where small percentage errors compound across thousands of hands. Study exploits for the spots that don't (river overbet shoves, very specific player tendencies) because GTO solutions in these spots are often nearly indifferent and player-specific reads matter more.

The preflop chart tool here gives you a starting point — the GTO baselines for the most common spots in 6-max and 9-max cash plus push/fold tournament play. The postflop solver gives you Monte Carlo equity for any board.