Dellacherie-style
A board evaluator in the Dellacherie tradition: landing height, transitions, wells and holes.
Rating
- 269,744
- ±10,020
- #2 of 9
- 269,744
Mean final score over 30 public seeds with gravity paused. The ± is a 95% t-interval across seeds. Beats Jev 1.13 on 29/30 seeds, DeepSeek V4 Flash on 30/30 seeds, GPT-5.6 Luna on 30/30 seeds, Qwen 3.7 Flash on 30/30 seeds, GPT-4o mini on 30/30 seeds and Random legal on 30/30 seeds. No evidence of a difference from Greedy heuristic and Two-ply search.
Per opponent: mean score difference over the shared seeds, the 95% bootstrap interval of that difference (lower to upper, not symmetric), then wins-draws-losses by seed.
Reliability
30/30 games · 14,881 calls · 100% answered · p50 0.12 ms · p95 0.21 ms
30/30 games · 14,881 calls · 100% answered before gravity moved · p50 0.11 ms · p95 0.20 ms
Latency covers completed calls only, measured from the question leaving the harness to the answer arriving. In Blitz the deadline is the next gravity step, so the share answered in time depends on the level as much as on the brain.
Replays
IQ · gravity paused
Blitz · real time
Notes
Footnotes
The Elo-style number is a penalised Bradley-Terry fit over IQ seed points, centred at 1500. It is a secondary view of the same games and does not enter the ranking. Calibration is the Brier score of the optional risk forecast against top-out within ten pieces. Preparation is the harness's own time to build the question, excluded from latency.