Play vs AI
Matches from 1 to 17 points or money games, with hints, Jacoby, beavers and the Crawford rule. Set how strong the engine plays.
The new Galaxy engine is the strongest backgammon engine ever built.
Free for Backgammon Galaxy Star and Star Pro members. Sign in with your Galaxy account.
Time is the average of one checker decision and one cube decision.
Ply notation: Galaxy, Sage and XG count the static evaluation as 1-ply, while GNU, Fox and Hedgehog count it as 0-ply. To compare like with like, GNU, Fox and Hedgehog are shown one ply higher than in their own notation on this page, so GNU 1P here is GNU 0-ply, GNU 2P is GNU 1-ply and GNU 3P is GNU 2-ply, and the same for Fox and Hedgehog.
Lines join the levels of the same engine. XG is eXtreme Gammon 2.10 at its Expert (1-ply), Professional (2-ply) and eXtremeGammon (3-ply) playing levels, placed from 7,632, 7,632 and 25,920 games against Galaxy 1P, 2P and 3P, without the Jacoby rule. XG's times (marked ~) are estimates, not measurements: they are read off XG's own published strength-vs-speed chart and scaled to our GNU timings, and XG 1P is not on that chart, so its time is a rough guess.
Hollow points are estimates from the 1,720 rolled-out positions database, not from simulations (hidden by default; turn them on with the "rollouts" buttons in the legend). Galaxy R1–R3, XG Roller+/Roller++ and Sage 1T/2T/3T are placed from their mean absolute equity error on 1,720 positions (against XG's and Galaxy's own rollouts, equal weight), using the relationship between that error and the simulated strength of the 1–3 ply engines, on a curve with diminishing returns (gains shrink as the error gets smaller). Galaxy R1, Sage 1T and XG Roller+ are drawn filled because they were measured in matches: R1 against Galaxy 3P (7,776 games), Sage 1T against Sage 3P on its Tiny filter (12,958 games) and Roller+ against XG's 3-ply (2,573 games); the curve is also calibrated on the R1 and Sage 1T results, and Sage 2T and 3T are shifted by Sage 1T's measured offset from the curve. Rollout times are per position; XG Roller++ time is a guess.
Mean absolute error of the no-double and double/take equities, in millipoints, lower is better. Galaxy R4 plays 1,296 trials to the end of the game. The two references differ by 19.3 on average, and on 38 of the 1,720 double/take calls.
Games played without the doubling cube, so only checker play counts.
Rollouts of the same 1,720 positions: mean absolute error of the ND and DT equities in millipoints against each reference, lower is better. Time is core-seconds per position for Galaxy.
| Rollout | Core-s/pos | vs Galaxy R4 | vs XG |
|---|---|---|---|
| Galaxy R41,296 trials, played to the end | – | ref. | 19.3 |
| Galaxy R3360 trials, truncated at 12 | 12.50 | 19.1 | 23.2 |
| XG rolloutXG's own rollouts of the set | – | 19.3 | ref. |
| Galaxy R2324 trials, truncated at 9 | 7.10 | 20.9 | 24.0 |
| XG Roller++ | – | 24.2 | 21.6 |
| Sage 3T | – | 24.7 | 27.4 |
| Galaxy R1144 trials, truncated at 7 | 1.70 | 26.8 | 27.9 |
| Sage 2T | – | 29.1 | 32.2 |
| XG Roller+ | – | 29.7 | 28.9 |
| GNU Roller B | – | 30.4 | 33.6 |
| Sage 1T | – | 35.1 | 37.2 |
± 1 standard error, fitted from the match-ups below and weighted by 1/SE². A difference of 0.01 ppg is one extra point per 100 games.
Millipoints per decision, lower is better: cubeless equity, no-double (ND) and double/take (DT) equity, and total cube error. Every engine at full depth with no move filter. Green marks the best in each column.
| Engine | Level 11P | Level 22P | Level 33P | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Cubeless | ND | DT | Cube err | Cubeless | ND | DT | Cube err | Cubeless | ND | DT | Cube err | |
| Galaxy | 23.9 | 52.3 | 63.4 | 3.38 | 16.7 | 36.7 | 57.8 | 1.76 | 12.6 | 28.5 | 41.2 | 0.74 |
| Sage | 32.0 | 63.1 | 90.5 | 5.98 | 22.6 | 51.9 | 65.2 | 3.21 | 18.8 | 34.6 | 57.2 | 1.82 |
| eXtreme Gammon | – | 62.1 | 87.3 | 6.17 | – | 49.0 | 61.5 | 3.04 | – | 35.0 | 55.2 | 1.77 |
| GNU Backgammon | 35.7 | 69.1 | 101.2 | 7.35 | 25.6 | 56.1 | 74.6 | 4.41 | 20.9 | 40.4 | 64.7 | 2.23 |
– not measured (XG reports no cubeless error at these settings). GNU is shown one level higher than in its own notation.
The 1,720 positions scored against Galaxy R4 instead of XG's rollouts. Cubeless is left out because R4's cubeless equity comes from cubeful trials.
| Engine | Level 11P | Level 22P | Level 33P | ||||||
|---|---|---|---|---|---|---|---|---|---|
| ND | DT | Cube err | ND | DT | Cube err | ND | DT | Cube err | |
| Galaxy | 53.8 | 65.6 | 3.74 | 37.0 | 58.8 | 1.93 | 28.8 | 41.1 | 1.09 |
| Sage | 64.0 | 89.1 | 5.80 | 52.2 | 63.1 | 3.12 | 34.2 | 55.0 | 1.84 |
| eXtreme Gammon | 63.3 | 88.5 | 6.30 | 49.6 | 62.9 | 3.20 | 35.7 | 56.2 | 2.06 |
| GNU Backgammon | 69.8 | 98.8 | 7.17 | 56.2 | 72.1 | 4.32 | 39.7 | 61.7 | 2.29 |
Mean is points per game for the first-named engine, with its 95% confidence interval. Where a match-up was run more than once, the runs are combined into one row: games are added up and the results are averaged, weighted by their precision. The engine that was ahead is in bold; bold numbers are significant. Galaxy 3P and XG 3P vs Sage 3P use Sage's Normal filter to match XG. Matches with Galaxy 2P and 3P, and every match against XG, are played without the Jacoby rule; the others with it. Fox and Hedgehog have no cube model of their own and use a fixed cube-efficiency formula.
| Mode | Match (A vs B) | Games | Mean ppg (A) | 95% CI |
|---|
Matches from 1 to 17 points or money games, with hints, Jacoby, beavers and the Crawford rule. Set how strong the engine plays.
Import .mat, .txt, .sgf and .xg files. Get every error, your error rate and Galaxy PR, and a chart of the turning points. Batch analyse up to 1,000 files at once.
Record an over-the-board match move by move with keyboard shortcuts. The engine analyses as you go and nothing is ever lost.
Allows transcribers, commentators and producer to be in sync. Live sessions share every move and the analysis as it happens.
Turn on Coach for a plain-language explanation of why the best play is best, for every position you review.
Paste an XGID or GNU ID, or build any position by hand, and analyse it in seconds.
Practise by playing out positions, and Gammon.ai scores them like a chouette or a manual rollout.
Cubeful rollouts tuned for Galaxy, from a 144-game quick check to 1,296 games played to the end. Or set up your own.
Every opening roll and reply, already rolled out for money and for match scores, so the first moves show rollout numbers straight away.
Save positions into your own folders, import XG position files and quiz yourself on your own blunder database.
State of the art stats breakdown of your game.
The new Galaxy Performance Rate (PR) weighs each decision by how difficult it is. That makes it different from the two similar metrics, Galaxy's Error Rate (ER) and XG's Performance Rating (also called PR). Mochy has been asking for this invention for decades, and we finally solved it.
The engine is installed with the app and uses all your processor cores. Analysis keeps working offline for up to 48 hours.
Read the user guide for every page and feature, step by step.
Gammon.ai comes with a Backgammon Galaxy Star or Star Pro membership. There is no separate account or password: sign in with Backgammon Galaxy and the app reads your membership.
| What you get | Star | Star Pro |
|---|---|---|
| Play vs AI, Analyze Match, Transcription, Set Up Position | ||
| Library, quizzes, Profiles, Batch Analysis | ||
| Analysis at 1-ply, 2-ply and 3-ply | ||
| Rolled-out opening book | ||
| Live sessions | ||
| Rollouts R1 to R4 and custom rollouts | – | |
| Super Deep and UBC match analysis presets | – |
Free to download. Sign in with a Backgammon Galaxy Star or Star Pro account to start.
AccountNo. You sign in with your normal Backgammon Galaxy account in your browser, and the app checks your membership. There is no extra password.
The download is free. Using the app needs a Backgammon Galaxy Star or Star Pro membership. Star gives you everything except rollouts; Star Pro adds rollouts and the deepest match analysis presets.
Yes. The engine runs on your own computer, so analysis keeps working offline for up to 48 hours after your last membership check. Sign-in, Coach and live sessions need a connection.
Yes. Gammon.ai opens .xg, .mat, .txt and .sgf match files, reads XGIDs and GNU Position IDs, and imports XG position files (.xgp) into your Library.
Yes. Error rate is measured the same way as in GNU Backgammon and eXtreme Gammon. Gammon.ai also shows Galaxy PR and a level of play from Casual to Super Grandmaster.
Yes! Galaxy is significantly stronger than eXtreme Gammon at 1-ply, 2-ply and 3-ply.
We play it against other engines over tens of thousands of games per match-up, and score every engine on eXtreme Gammon's own 1,720 rolled-out positions. At matching depth Galaxy came out ahead in every head-to-head we ran, and it has the lowest error at every level. The numbers are in Benchmarks above.
1P, 2P and 3P are how far the engine looks ahead: its direct judgement, one roll ahead and two rolls ahead. R1 to R4 are rollouts, where the position is played out 144 to 1,296 times and averaged.
Not yet. The Mac version needs Apple Silicon (M1 or newer), and Windows needs a 64-bit PC with Windows 10 or 11.
Play backgammon online against players from around the world, join tournaments and manage your Star or Star Pro membership.
Go to Backgammon GalaxyDownload Gammon.ai and sign in with Backgammon Galaxy.