program · League 1

GNUbg weak

FinishedPublished

Results f24d1f41, updated 16 November 2026, 21:24 UTC; scored by GNU Backgammon 1.08, 2-ply.

How we called it

Model ID
Missing
Provider or endpoint
GNU Backgammon 1.08, Beginner level (0-ply, noise 0.060), x86-64 build (see About the anchor)
Date run
2026-10-16 to 2026-10-22
Price
Missing
Model type
program
Weights
Missing
Runs on
CPU
Reasoning setting
Missing
Confidence source
none
Rules text
Missing
Option groups
not recorded; no decision in this data was split
Sampling settings
Missing
Notes
GNU Backgammon 1.08, Beginner level (0-ply, deterministic noise 0.060); fixed anchor in every league

Results in League 1

Error rate (PR)
21.418.8 to 24.3
Decisions
1,744 (1,744 scored, 0 invalid)
Engine's best play
52.0%
Blunder rate
19.0%
P95 equity loss
0.217
Mean loss, worst 5%
0.312
Median / P90 s per decision
0.01 / 0.01
$ per 1,000 decisions
Not measured
Risk judgement, margin 0.001
67.1 (95% interval 63.8 to 70.3); risks found 66.6% (410 / 616), right safety 67.6% (533 / 788)
Risk judgement, margin 0.02
64.3 (95% interval 61.1 to 67.5); risks found 66.1% (345 / 522), right safety 62.6% (552 / 882)
No trade-off
340 (left out of every risk metric)

JSON

Risk call card

67.1risk judgement, margin 0.001

right risks410
wrong risks140
needless risks255
missed risks66
right safety533

Hit risk only: being hit. Gammon risk and priming are not in it.

Close choices

A decision is a close choice when the second most likely play has at least half the probability of the first (internally: split).

Probabilities over plays, not sampled reasoning. Method

Decisions
1,744
Eligible (full probability distribution)
0
Left out, by reason
one letter only, or a program 1,744
Close choices
N/A no full probability distribution

By game phase

PhaseError rate (PR)Decisions
Opening35.2221
Contact22.81,254
Holding gameToo few decisions14
RaceToo few decisions184
Bear-offToo few decisions71