Skip to content
Duelwise
Sign in

The AI, measured

One opponent per game. Strength numbers come from tests or counted matches; an unmeasured level is in training.

Watch the AI learn

Human win rate vs Marlow, by week

0%15%30%45%60%75%90%Sep 10Sep 17Sep 24Oct 1Oct 8Oct 15Oct 22Oct 29Week of Oct 29: 100% (1 of 1 matches), too few matches to trust100%
Each point is a week of finished human matches against Marlow.solid: 30 or more matches. Dashed and hollow: too few matches to trust.
Heads-Up Hold'em trains by self-play and test bots.

Heads-Up Hold'em trains by self-play and against test bots, not from your matches yet. Your match is recorded for your report and the board.

  1. v1, champion Nov 4adjacent levels. 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.

Heads-Up Hold'em agent

Does not learn from site matches yet. Matches here are recorded for the player and are not used for training. It also trains on self-play.

Humans win vs Hard, last 7 days

100%

1 of 1 counted matches

Current version

v1

promoted Nov 4

Matches vs humans

14

14 passed the filters

Champion strength

1338

site Elo, measured

Human win rate by level

weekly, last eight weeks, counted matches only

Not enough weekly results to chart yet.

Levels, measured strength and limits
Easy87.2% (84.9% to 89.1%, 1000 games)score vs always-call1000
Medium68.3% (65.4% to 71.1%, 1000 games)score vs easy1133
Hard66.5% (63.5% to 69.4%, 1000 games)score vs medium1252
Champion62.1% (59.0% to 65.0%, 1000 games)score vs hard1338

Head to head

stronger level's score against the level below, with its confidence interval

  • Medium vs Easy68.3%stronger wins, 1000 games65.4% to 71.1%
  • Hard vs Medium66.5%stronger wins, 1000 games63.5% to 69.4%
  • Champion vs Hard62.1%stronger wins, 1000 games59.0% to 65.0%

Version history

  1. v1All levels measured. First version. Self-play only. Nov 4

Human matches, Heads-Up Hold'em

where they go

  • Played24
  • Finished14
  • Passed every filter14
  • Allowed for training0
  • Used for training0

Nothing is used for training yet. 0 opted-out matches never leave the database. 14 not used: this agent does not learn from people yet.

  • 4 resigned
  • 6 abandoned

What changed

measured, not described

No measured change is recorded for this version.