The most accurate
League of Legends
draft tool.

Most draft tools add up champion-vs-champion win rates with fixed formulas. LoLDraftAI uses a neural network trained on millions of ranked games, so it also picks up team-wide effects such as synergies, damage types and scaling that pair statistics miss. It's re-trained every patch.

DraftGap, iTero, and LoLTheory all rely on champion-vs-champion matchup statistics. They evaluate a draft as a list of pairs. LoLDraftAI is a neural network that reads the whole draft together, so it can reason about things like a team's damage profile or scaling. It outperforms all three on real matches that none of the tools had seen before. See the DraftGap, iTero, and LoLTheory comparisons for the numbers.

LoLDraftAI picks runes with the whole draft in mind: your team, the enemy team and every matchup. Most rune tools only look at your champion or a single matchup. The rune model is built on the draft model, so it knows how champions interact.

Yes. LoLDraftAI recommends a full item build conditioned on the entire draft: your champion, both teams, your runes and summoner spells, elo, and patch. You get the final build plus the purchase order, and on the desktop app you can apply it to your League client as an item set in one click.

Not at all. LoLDraftAI uses a custom-trained machine learning model built specifically for League of Legends draft prediction. It is trained on millions of real ranked games and learns the complex relationships between champions, matchups, synergies, team compositions, and game dynamics, directly from match outcomes. Learn more about how it works.

It predicts the winner from the draft alone 56.7% of the time (57.7% with runes), which is a lot given that draft is only one part of a game. It's also well calibrated: drafts it rates at 55% win about 55% of the time. In our study, taking its top suggestion as the last pick raised the team's predicted win rate by 4 to 7 points on average. See the per-pick lift study for the full curve.

The model evaluates the strength of a draft composition as a whole. Since the Riot API does not provide pick order data, the model is not inherently counter-pick aware. However, LoLDraftAI offers an “Account for counterpicks” option in champion suggestions. It lowers each win rate by how much that champion usually suffers when counterpicked, which helps you find safe blind picks.

Every patch. New patches usually land on Thursday and the model updates by Saturday, once there are enough games. You can use it on day one: synergies and counters barely change between patches.