The AI, measured
One opponent per game. Strength numbers come from tests or counted matches; an unmeasured level is in training.
Twelve Yards against people
Human win rate vs Marlow, by week
Twelve Yards is not a learned model: Pip keeps a favourite corner and a favourite dive; the other three are small programs that read the kicks and dives so far in this match. There is nothing to train. Your match is recorded for your report and the board.
- v1, champion Nov 4Each level beat the level below, and Pip beat random legal play, from both seats over 1000 games a seat. No human matches used.
What is site Elo?
Site Elo is a strength number we measure by playing the levels against each other. Easy is pinned at 1000 and every other level is placed from its results against the one below. A gap of 200 points means the stronger side is expected to win about three games in four (76 in 100, counting a draw as half). It is not a FIDE or chess.com rating, so it says nothing about how you would score against people.
- ChessVersion v1Humans win vs Hard, 7 days60%no earlier version to compareall fourNot yetnone yet
- Four in a RowVersion v2Humans win vs Hard, 7 days15%no earlier version to compareall fourTrains on site matchesv2, promoted
- Heads-Up Hold'emVersion v1Humans win vs Hard, 7 days100%no earlier version to compareall fourNot yetnone yet
- Word DuelVersion v1Humans win vs Hard, 7 days13%no earlier version to compareall fourNot yetnone yet
- TinderboxVersion v1Humans win vs Hard, 7 daysno matches yetall fourNot yetnone yet
- ColdstoreVersion v1Humans win vs Hard, 7 days50%no earlier version to compareall fourNot yetnone yet
- StormglassVersion v1Humans win vs Hard, 7 days50%no earlier version to compareall fourScriptednone yet
- CrosscurrentVersion v1Humans win vs Hard, 7 daysno matches yetall fourScriptednone yet
- Twelve YardsVersion v1Humans win vs Hard, 7 days29%no earlier version to compareall fourScriptednone yet
Twelve Yards agent
Hand-written habit reader: does not learn from site matches, because there is nothing to train.
Humans win vs Hard, last 7 days
29%
2 of 7 counted matches
Current version
v1
promoted Nov 4
Matches vs humans
14
14 passed the filters
Champion strength
1151
site Elo, measured
Human win rate by level
weekly, last eight weeks, counted matches only
Not enough weekly results to chart yet.
| Level | Measured | Site Elo |
|---|---|---|
| Easy | 61.1% (58.9% to 63.2%, 2000 games)score vs random | 1000 |
| Medium | 58.9% (56.7% to 61.0%, 2000 games)score vs easy | 1062 |
| Hard | 56.3% (54.1% to 58.4%, 2000 games)score vs medium | 1106 |
| Champion | 56.4% (54.2% to 58.6%, 2000 games)score vs hard | 1151 |
Head to head
stronger level's score against the level below, with its confidence interval
- Medium vs Easy58.9%stronger wins, 2000 games56.7% to 61.0%
- Hard vs Medium56.3%stronger wins, 2000 games54.1% to 58.4%
- Champion vs Hard56.4%stronger wins, 2000 games54.2% to 58.6%
Version history
- v1All levels measured. First version. No human matches used. Nov 4
Human matches, Twelve Yards
where they go
- Played15
- Finished14
- Passed every filter14
- Allowed for training0
- Used for training0
Nothing is used for training. 0 opted-out matches never leave the database. 14 not used: this agent is scripted and has nothing to train.
- 1 resigned
What changed
measured, not described
No measured change is recorded for this version.