The AI, measured
One opponent per game. Strength numbers come from tests or counted matches; an unmeasured level is in training.
Stormglass against people
Human win rate vs Marlow, by week
Stormglass is a scripted solver, not a learned model: each level is a different algorithm, so there is nothing to train. Your match is recorded for your report and the board.
- v1, champion Nov 2Each level beat the level below, and Pip beat random legal play, from both seats over 400 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
Stormglass agent
Scripted solver: does not learn from site matches, because there is nothing to train.
Humans win vs Hard, last 7 days
50%
1 of 2 counted matches
Current version
v1
promoted Nov 2
Matches vs humans
9
9 passed the filters
Champion strength
1637
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 | 97.8% (96.5% to 98.6%, 800 games)score vs random | 1000 |
| Medium | 88.3% (85.8% to 90.3%, 800 games)score vs easy | 1350 |
| Hard | 72.9% (69.7% to 75.8%, 800 games)score vs medium | 1522 |
| Champion | 66.0% (62.6% to 69.2%, 800 games)score vs hard | 1637 |
Head to head
stronger level's score against the level below, with its confidence interval
- Medium vs Easy88.3%stronger wins, 800 games85.8% to 90.3%
- Hard vs Medium72.9%stronger wins, 800 games69.7% to 75.8%
- Champion vs Hard66.0%stronger wins, 800 games62.6% to 69.2%
Version history
- v1All levels measured. First version. No human matches used. Nov 2
Human matches, Stormglass
where they go
- Played14
- Finished9
- Passed every filter9
- Allowed for training0
- Used for training0
Nothing is used for training. 0 opted-out matches never leave the database. 9 not used: this agent is scripted and has nothing to train.
- 5 resigned
What changed
measured, not described
No measured change is recorded for this version.