MattBench MattBench dan’s tests n9x.co

dan’s tests

New test

Finished 25 shown

AuthorEngineIdentifierCodeTime control
Results
dan Hobbes feature/best-move-red-hist
#4924 Finished
diff ↗ 8.0+0.08 LLR: -1.21 (-2.23, 2.55) [0.00, 4.00]
Games: 9232 W: 2383 L: 2410 D: 4439
Ptnml(0-2): 53, 1062, 2402, 1057, 42
dan Hobbes feature/best-move-red-hist
#4923 Finished
diff ↗ 8.0+0.08 LLR: -0.55 (-2.23, 2.55) [0.00, 4.00]
Games: 928 W: 222 L: 243 D: 463
Ptnml(0-2): 4, 110, 257, 89, 4
dan Hobbes feature/rfp-allow-tt-upper
#4922 Finished
diff ↗ 8.0+0.08 LLR: -1.27 (-2.23, 2.55) [0.00, 4.00]
Games: 14324 W: 3726 L: 3740 D: 6858
Ptnml(0-2): 60, 1548, 3953, 1548, 53
dan Hobbes feature/nmp-improving-red
#4921 Failed
diff ↗ 8.0+0.08 LLR: -2.26 (-2.25, 2.89) [0.00, 4.00]
Games: 11020 W: 2740 L: 2810 D: 5470
Ptnml(0-2): 50, 1351, 2788, 1261, 60
dan Hobbes feature/standpat-tt-store
#4920 Finished
diff ↗ 8.0+0.08 LLR: -0.81 (-2.25, 2.89) [0.00, 4.00]
Games: 7994 W: 2047 L: 2060 D: 3887
Ptnml(0-2): 40, 981, 1979, 946, 51
dan Hobbes main
#4919 Passed
diff ↗ 8.0+0.08 Elo: 70.75 +- 5.62 (95%) [N=5000]
Games: 5008 W: 1912 L: 906 D: 2190
Ptnml(0-2): 15, 273, 1070, 983, 163
dan Hobbes feature/early-static-eval-tt
#4917 Passed
diff ↗ 8.0+0.08 LLR: 3.00 (-2.25, 2.89) [0.00, 4.00]
Games: 4284 W: 1188 L: 1038 D: 2058
Ptnml(0-2): 11, 461, 1061, 585, 24
dan Hobbes feature/conthist-mainhist-base
#4913 Finished
diff ↗ 40.0+0.40 LLR: -2.07 (-2.25, 2.89) [0.00, 4.00]
Games: 2916 W: 669 L: 750 D: 1497
Ptnml(0-2): 4, 383, 766, 300, 5
dan Hobbes feature/conthist-mainhist-base
#4912 Failed
diff ↗ 8.0+0.08 LLR: -2.27 (-2.25, 2.89) [0.00, 4.00]
Games: 19852 W: 4951 L: 4995 D: 9906
Ptnml(0-2): 107, 2403, 4940, 2379, 97
dan Hobbes feature/spsa-6-test
#4902 Passed
diff ↗ 40.0+0.40 LLR: 2.94 (-2.25, 2.89) [0.00, 4.00]
Games: 27682 W: 6799 L: 6592 D: 14291
Ptnml(0-2): 35, 3194, 7187, 3379, 46
dan Hobbes feature/spsa-6
#4887 Finished
diff ↗ 40.0+0.40 Tuning 101 Parameters
5000/5000 Iterations
40002/40000 Games Played
dan Hobbes feature/multicut-fail-firm
#4893 Passed
diff ↗ 8.0+0.08 LLR: 2.68 (-2.23, 2.55) [0.00, 4.00]
Games: 22206 W: 5786 L: 5600 D: 10820
Ptnml(0-2): 86, 2502, 5755, 2660, 100
dan Hobbes feature/capthist-threats-2
#4884 Failed
diff ↗ 8.0+0.08 LLR: -2.37 (-2.23, 2.55) [0.00, 4.00]
Games: 7262 W: 1862 L: 1948 D: 3452
Ptnml(0-2): 40, 887, 1853, 821, 30
dan Hobbes feature/yoshie-conthist
#4854 Finished
diff ↗ 8.0+0.08 LLR: -1.62 (-2.23, 2.55) [0.00, 4.00]
Games: 11688 W: 3001 L: 3039 D: 5648
Ptnml(0-2): 36, 1404, 3028, 1314, 62
dan Hobbes feature/max-eval-incorrectness
#4881 Failed
diff ↗ 8.0+0.08 LLR: -2.24 (-2.23, 2.55) [0.00, 4.00]
Games: 5006 W: 1329 L: 1417 D: 2260
Ptnml(0-2): 21, 653, 1252, 547, 30
dan Hobbes feature/higher-final-wdl
#4878 Failed
diff ↗ 8.0+0.08 LLR: -2.30 (-2.23, 2.55) [0.00, 4.00]
Games: 682 W: 133 L: 252 D: 297
Ptnml(0-2): 11, 133, 162, 34, 1
dan Hobbes feature/output-buckets
#4874 Failed
diff ↗ 8.0+0.08 LLR: -2.23 (-2.23, 2.55) [0.00, 4.00]
Games: 8396 W: 2227 L: 2304 D: 3865
Ptnml(0-2): 53, 1007, 2147, 946, 45
dan Hobbes feature/moar-finetuning
#4860 Failed
diff ↗ 8.0+0.08 LLR: -2.24 (-2.23, 2.55) [0.00, 4.00]
Games: 4886 W: 1317 L: 1405 D: 2164
Ptnml(0-2): 25, 616, 1259, 508, 35
dan Hobbes feature/wdl-filtering
#4856 Failed
diff ↗ 8.0+0.08 LLR: -2.26 (-2.23, 2.55) [0.00, 4.00]
Games: 1066 W: 255 L: 357 D: 454
Ptnml(0-2): 15, 164, 263, 90, 1
dan Hobbes feature/yoshie-conthist
#4853 Failed
diff ↗ 8.0+0.08 LLR: -2.27 (-2.23, 2.55) [0.00, 4.00]
Games: 542 W: 83 L: 223 D: 236
Ptnml(0-2): 17, 124, 112, 18, 0
dan Hobbes main
#4852 Finished
diff ↗ 8.0+0.08 Elo: 63.49 +- 6.76 (95%) [N=5000]
Games: 3292 W: 1230 L: 635 D: 1427
Ptnml(0-2): 12, 177, 754, 610, 93
dan Hobbes feature/lazy-nnue-updates
#4849 Passed
diff ↗ 4.0+0.04 LLR: 2.60 (-2.23, 2.55) [0.00, 4.00]
Games: 2322 W: 703 L: 574 D: 1045
Ptnml(0-2): 14, 203, 609, 310, 25
dan Hobbes feature/1536-hl
#4834 Failed
diff ↗ 8.0+0.08 LLR: -2.37 (-2.23, 2.55) [0.00, 4.00]
Games: 4230 W: 1118 L: 1216 D: 1896
Ptnml(0-2): 26, 558, 1048, 454, 29
dan Hobbes feature/piece-count-distro-filtering
#4825 Failed
diff ↗ 8.0+0.08 LLR: -2.24 (-2.23, 2.55) [0.00, 4.00]
Games: 11448 W: 3100 L: 3168 D: 5180
Ptnml(0-2): 69, 1351, 2949, 1289, 66
dan Hobbes feature/mate-scores-corrhist
#4800 Passed
diff ↗ 8.0+0.08 LLR: 2.60 (-2.23, 2.55) [0.00, 4.00]
Games: 28480 W: 7483 L: 7282 D: 13715
Ptnml(0-2): 102, 3241, 7397, 3354, 146