Free tools Windows power users keep installed
One-click scans. No signup required.
Ataraxos, a Stratego-playing AI, defeated Pim Niemeijer—described by the authors of a 2026 Nature paper as the game’s most decorated player of all time—in a 20-game series. Ataraxos won 15 games, lost one and drew four. Counting each draw as half a win, the authors calculated an 85% effective win rate. The result belongs to Ataraxos, not DeepNash, the earlier AI that reached expert-level play and a top-three ranking on Gravon.
What happened in the match against Pim Niemeijer?
The 20-game series took place over three weeks. Ataraxos finished with 15 wins, one loss and four draws. The 2026 paper reports an 85% effective win rate, a calculation that counts each draw as half a win. That is the direct basis for saying an AI beat Stratego’s greatest player.
The result is a match-series outcome, not a tournament title or a claim that Ataraxos is unbeatable. The distinction matters: the evidence is a specific set of games against one highly accomplished opponent.
How does this differ from DeepNash’s earlier Stratego milestone?
DeepNash, developed by Google DeepMind, made a separate breakthrough reported in 2022. DeepMind said it won more than 97% of its games against leading Stratego bots and 84% against top expert humans on the Gravon online platform, where it also attained an all-time top-three ranking. Those results established strong play in that evaluation; they were not a victory over Niemeijer.
The Tool Desk
Outbyte Driver Updater FREEScan for outdated or missing drivers - takes under a minuteDriver Scan →Outbyte PC Repair FREERepair Windows errors before they cause bigger problemsFix Now →#1 Best Overall
- Stratego is the strategic game where you challenge your opponents in the heat of battle
- Your task is to capture your opponent’s flag while defending your own
- Lead your men into battle, every move is crucial
- Includes 2 x 40 pre-printed playing pieces, Game board, Screen and 2 sorting trays for the pieces
- Suitable for 2 players, aged 8+
A later evaluation in the 2026 paper adds important context. Its authors counted DeepNash’s 2022 Gravon human result as 42 wins in 50 games, but said Gravon’s player pool had diminished and the opponents matched there were far from top-human level. Those players also did not know they were facing a bot. In a 2023 World Championship demonstration, DeepNash went 19–9; the paper says it lost to most of the highest-ranked players who played it, including Niemeijer.
| System and evaluation | Reported result | What the result represents |
|---|---|---|
| DeepNash vs. leading bots | More than 97% wins, often 100% | DeepMind’s 2022 report of matches against leading Stratego bots. |
| DeepNash vs. Gravon human opponents | 84% reported win rate; top-three all-time Gravon ranking | DeepMind’s 2022 account; the 2026 paper later characterized the matched player pool as far below top-human level. |
| DeepNash at the 2023 World Championship demonstration | 19 wins, 9 losses | A demonstration, not a tournament championship result. |
| Ataraxos vs. Pim Niemeijer | 15 wins, 1 loss, 4 draws; 85% effective win rate | A 20-game series over three weeks, reported in 2026; draws count as half a win for the effective rate. |
| Ataraxos vs. 2025 World Championship attendees | 38 wins, 2 losses, no draws; 95% effective win rate | A 40-game demonstration against attendees, not a World Championship tournament result. |
These percentages should not be read as a head-to-head comparison between the AIs. The systems faced different opponents in different settings, and DeepNash’s Gravon evaluation, Ataraxos’ series against Niemeijer and the championship demonstrations were distinct kinds of evidence.
Rank #2
- Test your skill with Stratego, a classic game of battlefield strategy
- Let battle commence between Assassins and Templars in this ‘Stratego Assassins Creed’ special edition
- Attack and be the first to capture your opponent’s Apple of Eden Play three exciting variations of the game: Classic, Duel, and Special
- Includes 30 red playing pieces, 30 blue playing pieces, game board, screen, and sticker sheet
- Suitable for 2 players, aged 8+
Why is Stratego difficult for an AI?
Stratego is a two-player game in which each player secretly arranges their pieces. Players cannot see the opponent’s ranks at the start, so they must infer them through encounters and play around uncertainty. DeepMind describes the challenge as combining long-term strategy, bluffing, information gathering and manoeuvring.
That hidden information changes the problem from simply calculating the best move on a visible board. A player must decide what an unknown piece might be, what the opponent may believe, and when to reveal or conceal information. A strong strategy must also avoid becoming predictable: an opponent who learns a player’s habits can exploit them.
Recommended Free Tools
Rank #3
- The classic game of battlefield strategy!
- It's a light strategy game for two players
- Command your Army, devise plans using strategic attacks and clever deception!
- Be the first player to capture the other Army's flag to win!
- For ages 8 and up
How did DeepNash learn to play?
DeepNash used model-free deep reinforcement learning and self-play, guided by game-theoretic ideas. It learned from playing games rather than relying on a search procedure that looks ahead through possible move sequences. DeepMind reported that the system varied its starting deployments and randomized among actions it considered equivalent, making its play harder to predict and exploit.
DeepMind quoted Vincent de Boer, a co-author and former Stratego world champion, on the system’s level: “The level of play of DeepNash surprised me. I had never heard of an artificial Stratego player that came close to the level needed to win a match against an experienced human player. But after playing against DeepNash myself, I wasn’t surprised by the top-3 ranking it later achieved on the Gravon platform.” That assessment reflects DeepNash’s significance as an early expert-level Stratego AI; it does not change the later evidence about its results against the strongest players.
Rank #4
- Strategy Board Game
- Players: 2
- Age: 8 and up
What does Ataraxos’ result establish?
Ataraxos’ 20-game series shows that an AI can defeat a player the paper identifies as Stratego’s most decorated of all time across a substantial match series. It is a striking benchmark in a game where hidden information makes reliable play especially demanding.
The same paper reports another Ataraxos evaluation: 38 wins, two losses and no draws in 40 games against attendees at the 2025 Stratego World Championship, a 95% effective win rate. This was a demonstration against attendees, not a tournament result. Neither that event nor the Niemeijer series makes a direct comparison with DeepNash possible; no DeepNash-versus-Ataraxos match is reported in the cited accounts.
Quick Recap
Best Value
- Brand New in box. The product ships with all relevant accessories
- Includes gameboard, armies with 4 Infantry, 12 Cavalry, and 8 Artillery each, deck of 56 Risk cards, 1 card box, 5 dice, 5 cardboard war crates, and game guide.
- PLAY USING ALEXA SKILL: Players have the option of playing this Risk game using Alexa. (Alexa device sold separately. ) Note: sound comes from paired Echo device.
- DRAGON TOKEN: This Risk game includes a dragon token. Players must destroy the dragon before it destroys their troops. A lucky roll can subdue the dragon and get it out of a player's territory
Sources
- Google DeepMind: DeepNash and its 2022 Stratego results
- Nature: 2026 paper reporting Ataraxos and revisiting DeepNash’s evaluations
- PubMed record for the DeepNash Science paper
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
