OpenBench Testing Framework

Active : 44 Machines / 344 Threads / 501.04 MNPS
Priority 0
ClaudeIncipitg7-3gen-4C56329Ediff10.0+0.10LLR: 2.41 (-2.94, 2.94) [0.00, 2.00]
Games: 37540 W: 9118 L: 8828 D: 19594
Ptnml(0-2): 242, 4506, 9062, 4640, 320
[sn1] 3 generations (c5-c7) vs 2 (c6-c7)
AtlasCodanet-691C30F4diff10.0+0.10LLR: 0.53 (-2.94, 2.94) [0.00, 2.00]
Games: 22442 W: 5585 L: 5505 D: 11352
Ptnml(0-2): 62, 2654, 5719, 2714, 72
[atlas] Decay tail 2 on the zero-blend lineage, testing whether the second tail is still worth its old +2.4.
ClaudeIncipitmaindiffN=15000Generated 1029184/1500000 Games
Elo: -0.21 +- 0.54 (95%) [N=1500000]
Games: 1029184 W: 332201 L: 332817 D: 364166
[sn1] gen c8 from 849C3939: 1.5M games N=15000
ClaudeIncipitmaindiff10.0+0.10Tuning 27 Parameters
6904/40000 Iterations
27616/160000 Games Played
[sn1] full SPSA on 5448A4FD: 40k iters x 2 pairs
ClaudeIncipitmaindiffN=15000Generated 420464/1500000 Games
Elo: -0.72 +- 0.84 (95%) [N=1500000]
Games: 420464 W: 134846 L: 135713 D: 149905
[sn1] extra datagen from 5448A4FD (c8b): 1.5M games N=15000
Finished
ClaudeIncipitg7-c4to7-FE9B7FA3diff10.0+0.10LLR: -2.98 (-2.94, 2.94) [0.00, 2.00]
Games: 9520 W: 2165 L: 2436 D: 4919
Ptnml(0-2): 80, 1287, 2281, 1048, 64
[sn1] gens 4-7 (~720M) vs gens 6-7
ClaudeIncipitpairwisediff10.0+0.10LLR: -1.75 (-2.94, 2.94) [0.00, 2.00]
Games: 5528 W: 1263 L: 1426 D: 2839
Ptnml(0-2): 60, 749, 1288, 628, 39
[sn1] FT 768pw vs 768 SCReLU (gen 7 recipe)
ClaudeIncipitpairwisediff10.0+0.10LLR: -2.95 (-2.94, 2.94) [0.00, 2.00]
Games: 4094 W: 866 L: 1155 D: 2073
Ptnml(0-2): 51, 647, 913, 412, 24
[sn1] FT 512pw vs 768 SCReLU (gen 7 recipe)
ClaudeIncipitkbcachediffN=25000LLR: -2.98 (-2.94, 2.94) [0.00, 2.00]
Games: 12458 W: 3522 L: 3851 D: 5085
Ptnml(0-2): 393, 1586, 2509, 1439, 302
[sn1] kb4 vs main at FIXED NODES (eval quality only)
ClaudeIncipitpairwisediff10.0+0.10LLR: -0.81 (-2.94, 2.94) [-5.00, 0.00]
Games: 12794 W: 2804 L: 2877 D: 7113
Ptnml(0-2): 63, 1348, 3631, 1309, 46
[sn1] non-regression: pairwise support, branchless eval
ClaudeIncipitg7-kb8-9FF59087diff10.0+0.10LLR: -1.93 (-2.94, 2.94) [0.00, 2.00]
Games: 1532 W: 280 L: 475 D: 777
Ptnml(0-2): 33, 263, 340, 126, 4
[sn1] 8 king buckets vs none (gen 7 recipe)
ClaudeIncipitpairwisediff10.0+0.10LLR: -1.05 (-2.94, 2.94) [-2.00, 1.00]
Games: 11400 W: 2528 L: 2597 D: 6275
Ptnml(0-2): 44, 1281, 3127, 1196, 52
[sn1] non-regression: pairwise support (no net change)
ClaudeIncipitg7-c6c7-768-5448A4FDdiff10.0+0.10LLR: 2.95 (-2.94, 2.94) [0.00, 2.00]
Games: 10166 W: 2641 L: 2338 D: 5187
Ptnml(0-2): 59, 1161, 2387, 1370, 106
[sn1] gen 7 net (c6+c7, FT 768) vs 849C3939
ClaudeIncipitmaindiffN=15000Generated 1500036/1500000 Games
Elo: -0.00 +- 0.45 (95%) [N=1500000]
Games: 1500036 W: 484471 L: 484482 D: 531083
[sn1] gen c7 from 849C3939: 1.5M games N=15000
ClaudeIncipitg6-160-4679A26Ddiff10.0+0.10LLR: 1.22 (-2.94, 2.94) [0.00, 2.00]
Games: 23906 W: 5869 L: 5714 D: 12323
Ptnml(0-2): 181, 2851, 5735, 3004, 182
[sn1] 160 SB vs 80 SB (gen 6 recipe)
ClaudeIncipitg6-w30-7C683845diff10.0+0.10LLR: -2.97 (-2.94, 2.94) [-1.50, 1.50]
Games: 9074 W: 2125 L: 2317 D: 4632
Ptnml(0-2): 90, 1174, 2180, 1024, 69
[sn1] lambda 0.7 vs 0.85 (gen 6 recipe)
ClaudeIncipitmaindiffN=15000Generated 495534/1500000 Games
Elo: 0.38 +- 0.78 (95%) [N=1500000]
Games: 495534 W: 162524 L: 161988 D: 171022
[sn1] gen c7 from 2CBCC7E0: 1.5M games N=15000
ClaudeIncipitg6-c5c6-768-849C3939diff10.0+0.10LLR: 2.96 (-2.94, 2.94) [0.00, 2.00]
Games: 2846 W: 832 L: 532 D: 1482
Ptnml(0-2): 7, 262, 621, 490, 43
[sn1] gen 6 net (c5+c6, FT 768) vs 2CBCC7E0
ClaudeIncipitmaindiffN=15000Generated 1500020/1500000 Games
Elo: -0.13 +- 0.45 (95%) [N=1500000]
Games: 1500020 W: 493285 L: 493850 D: 512885
[sn1] gen c6 from 7F72F973: 1.5M games N=15000
ClaudeIncipitg5-c4c5-768-2CBCC7E0diff10.0+0.10LLR: 2.97 (-2.94, 2.94) [0.00, 2.00]
Games: 13694 W: 3573 L: 3258 D: 6863
Ptnml(0-2): 115, 1550, 3242, 1785, 155
[sn1] FT 768 vs 512 (gen 5 data)
ClaudeIncipitmaindiffN=15000Generated 452298/1500000 Games
Elo: 0.11 +- 0.83 (95%) [N=1500000]
Games: 452298 W: 152032 L: 151891 D: 148375
[sn1] gen c6 from F8CA057A: 1.5M games N=15000
ClaudeIncipitg5-c4c5-80-7F72F973diff10.0+0.10LLR: 2.95 (-2.94, 2.94) [0.00, 2.00]
Games: 2070 W: 708 L: 386 D: 976
Ptnml(0-2): 9, 140, 455, 382, 49
[sn1] gen 5 net (c4+c5, 80 SB) vs F8CA057A
ClaudeIncipitmaindiffN=15000Generated 1500232/1500000 Games
Elo: 0.29 +- 0.46 (95%) [N=1500000]
Games: 1500232 W: 504241 L: 502979 D: 493012
[sn1] gen c5 from 765C79CD: 1.5M games N=15000
ClaudeIncipitg4-c3c4-80-F8CA057Adiff10.0+0.10LLR: 2.96 (-2.94, 2.94) [0.00, 2.00]
Games: 10632 W: 2913 L: 2595 D: 5124
Ptnml(0-2): 101, 1206, 2423, 1446, 140
[sn1] 80 SB vs 40 SB (c3+c4)
ClaudeIncipitmaindiffN=15000Generated 222684/1500000 Games
Elo: -0.31 +- 1.18 (95%) [N=1500000]
Games: 222684 W: 74863 L: 75059 D: 72762
[sn1] gen c5 from F0359B05: 1.5M games N=15000
ClaudeIncipitg4-c3c4-long-40-765C79CDdiff10.0+0.10LLR: 2.96 (-2.94, 2.94) [0.00, 2.00]
Games: 6496 W: 1862 L: 1543 D: 3091
Ptnml(0-2): 74, 670, 1476, 919, 109
[sn1] 40 SB vs 20 SB (c3+c4)
ClaudeIncipitmaindiff10.0+0.10Elo: 4.00 +- 6.52 (95%) [N=4000]
Games: 4000 W: 1071 L: 1025 D: 1904
Ptnml(0-2): 38, 532, 840, 526, 64
[sn1] c3+c4 net vs c4-only net
ClaudeIncipitmaindiffN=15000Generated 217944/1500000 Games
Elo: -0.67 +- 1.23 (95%) [N=1500000]
Games: 217944 W: 77384 L: 77802 D: 62758
[sn1] C3 datagen c4b: 1.5M games N=15000
ClaudeIncipitg4-c3c4-20-F0359B05diff10.0+0.10LLR: 3.08 (-2.94, 2.94) [0.00, 2.00]
Games: 1098 W: 623 L: 97 D: 378
Ptnml(0-2): 0, 17, 125, 271, 136
[sn1] g4-c3c4-20 vs C3
ClaudeIncipitg4-c4-15-2F16641Ddiff10.0+0.10LLR: 3.00 (-2.94, 2.94) [0.00, 2.00]
Games: 1100 W: 622 L: 110 D: 368
Ptnml(0-2): 3, 23, 123, 261, 140
[sn1] g4-c4-15 vs C3