Progression / Regression Tests

All of the information below has been generated from the results of tests performed on the Fishtest framework.

Current Testing Criteria

1 Thread 60 seconds + 0.6 seconds for 60,000 games (2019-11-21 - current)
8 Threads 60 seconds + 0.6 seconds for 60,000 games (2023-06-29 - current)
UHO_4060_v4.epd opening book (2025-04-26 - current)

Previous Testing Criteria

1 Thread 60 seconds + 0.6 seconds for 40,000 games (2016-01-02 - 2019-11-21)
1 Thread 60 seconds + 0.5 seconds for 40,000 games (2013-10-13 - 2016-01-02)
1 Thread 60 seconds + 0.5 seconds for 20,000 games (2013-03-04 - 2013-10-13)
8 Threads 30 seconds + 0.3 seconds for 40,000 games (2018-12-13 - 2023-06-29)
8moves_GM.pgn opening book (2013-04-10 - 2013-11-01)
varied.bin opening book (2013-03-04 - 2013-04-07)
8moves_v3.pgn opening book (2013-11-09 - 2023-06-29)
UHO_XXL_+0.90_+1.19.epd opening book (2022-04-17 - 2023-06-29)
UHO_4060_v2.epd opening book (2023-06-29 - 2023-09-10)
UHO_4060_v3.epd opening book (2023-09-10 - 2025-04-26)

Current Development

`Date`	`Version`	`1 Thread`	`8 Threads`
2024‑10‑12	master vs Stockfish 17 _{Bench: 1283457 Make low ply history size fixed [differences] 40}	Elo: 8.99 ±1.3 _{Ptnml: 48, 5604, 17142, 7159, 47 nElo: 19.27 ±2.8 PairsRatio: 1.27 [raw statistics]}	Elo: 4.85 ±1.1 _{Ptnml: 4, 4647, 19867, 5471, 11 nElo: 11.80 ±2.8 PairsRatio: 1.18 [raw statistics]}
2024‑11‑13	master vs Stockfish 17 _{Bench: 840721 Adjust statscore for captures [differences] 63}	Elo: 11.88 ±1.3 _{Ptnml: 34, 5232, 17427, 7263, 44 nElo: 25.85 ±2.8 PairsRatio: 1.39 [raw statistics]}	Elo: 4.81 ±1.1 _{Ptnml: 3, 4639, 19887, 5466, 5 nElo: 11.72 ±2.8 PairsRatio: 1.18 [raw statistics]}
2024‑12‑08	master vs Stockfish 17 _{Bench: 934447 Small Major/Minor piece key simplification/optimization. [differences] 81}	Elo: 13.02 ±1.3 _{Ptnml: 36, 5189, 17325, 7392, 58 nElo: 28.18 ±2.8 PairsRatio: 1.43 [raw statistics]}	Elo: 7.59 ±1.1 _{Ptnml: 9, 4389, 19890, 5707, 5 nElo: 18.49 ±2.8 PairsRatio: 1.30 [raw statistics]}
2025‑01‑06	master vs Stockfish 17 _{Bench: 999324 Remove non-functional std::min() [differences] 102}	Elo: 15.05 ±1.3 _{Ptnml: 33, 5044, 17264, 7611, 48 nElo: 32.62 ±2.8 PairsRatio: 1.51 [raw statistics]}	Elo: 4.81 ±1.1 _{Ptnml: 9, 4603, 19941, 5443, 4 nElo: 11.73 ±2.8 PairsRatio: 1.18 [raw statistics]}
2025‑01‑12	master vs Stockfish 17 _{Bench: 1379150 Increase the depth margin [differences] 118}	Elo: 10.87 ±1.3 _{Ptnml: 52, 5424, 17161, 7321, 42 nElo: 23.35 ±2.8 PairsRatio: 1.34 [raw statistics]}	Elo: 12.23 ±1.1 _{Ptnml: 8, 4024, 19823, 6138, 7 nElo: 29.85 ±2.8 PairsRatio: 1.52 [raw statistics]}
2025‑01‑25	master vs Stockfish 17 _{Bench: 1438043 Simplify futility margin in lmr for quiets. [differences] 150}	Elo: 16.96 ±1.3 _{Ptnml: 50, 4861, 17260, 7770, 59 nElo: 36.72 ±2.8 PairsRatio: 1.59 [raw statistics]}	Elo: 14.54 ±1.1 _{Ptnml: 3, 3796, 19893, 6304, 4 nElo: 35.75 ±2.8 PairsRatio: 1.66 [raw statistics]}
2025‑02‑04	master vs Stockfish 17 _{Bench: 2887850 Reduce less for positions without tt move [differences] 177}	Elo: 7.14 ±1.3 _{Ptnml: 68, 5808, 17016, 7039, 69 nElo: 15.14 ±2.8 PairsRatio: 1.21 [raw statistics]}	Elo: 14.61 ±1.1 _{Ptnml: 5, 3923, 19625, 6440, 7 nElo: 35.41 ±2.8 PairsRatio: 1.64 [raw statistics]}
2025‑02‑05	master vs Stockfish 17 _{Bench: 3197798 Increase PCM bonus when cutOffCnt is low [differences] 181}	Elo: 10.76 ±1.3 _{Ptnml: 43, 5526, 17030, 7333, 68 nElo: 22.94 ±2.8 PairsRatio: 1.33 [raw statistics]}	Elo: 15.31 ±1.1 _{Ptnml: 4, 3845, 19662, 6482, 7 nElo: 37.23 ±2.8 PairsRatio: 1.69 [raw statistics]}
2025‑02‑24	master vs Stockfish 17 _{Bench: 2146010 Simplify bestvalue update formula [differences] 200}	Elo: 19.43 ±1.3 _{Ptnml: 21, 4662, 17306, 7966, 45 nElo: 42.50 ±2.8 PairsRatio: 1.71 [raw statistics]}	Elo: 12.09 ±1.2 _{Ptnml: 7, 4157, 19584, 6246, 6 nElo: 29.15 ±2.8 PairsRatio: 1.50 [raw statistics]}
2025‑03‑21	master vs Stockfish 17 _{Bench: 2030154 Change layout of CorrectionHistory<NonPawn> [differences] 221}	Elo: 19.80 ±1.3 _{Ptnml: 30, 4563, 17419, 7938, 50 nElo: 43.44 ±2.8 PairsRatio: 1.74 [raw statistics]}	Elo: 18.76 ±1.1 _{Ptnml: 6, 3604, 19549, 6830, 11 nElo: 45.55 ±2.8 PairsRatio: 1.90 [raw statistics]}
2025‑03‑29	master vs Stockfish 17 _{Bench: 2030154 Silence "may be used uninitialized" GCC warning [differences] 225}	Elo: 20.35 ±1.3 _{Ptnml: 30, 4520, 17407, 7996, 47 nElo: 44.68 ±2.8 PairsRatio: 1.77 [raw statistics]}	Elo: 18.74 ±1.2 _{Ptnml: 2, 3650, 19472, 6864, 12 nElo: 45.37 ±2.8 PairsRatio: 1.88 [raw statistics]}
2025‑03‑30	Stockfish 17.1 _{Bench: 2030154 [differences] 226}
2025‑04‑18	master vs Stockfish 17 _{Bench: 1715901 Skip 5th continuation history [differences] 251}	Elo: 23.32 ±1.3 _{Ptnml: 22, 4433, 17100, 8392, 53 nElo: 50.84 ±2.8 PairsRatio: 1.90 [raw statistics]}	Elo: 19.67 ±1.2 _{Ptnml: 3, 3620, 19363, 7008, 6 nElo: 47.48 ±2.8 PairsRatio: 1.94 [raw statistics]}
2025‑04‑26	master vs Stockfish 17 _{Bench: 1585741 Allow some nodes to spawn even deeper lmr searches [differences] 268}	Elo: 20.35 ±1.3 _{Ptnml: 19, 4565, 17344, 8030, 42 nElo: 44.67 ±2.8 PairsRatio: 1.76 [raw statistics]}	Elo: 20.06 ±1.2 _{Ptnml: 2, 3572, 19398, 7019, 9 nElo: 48.52 ±2.8 PairsRatio: 1.97 [raw statistics]}
2025‑05‑13	master vs Stockfish 17 _{Bench: 2251724 Introducing a depth component to the penalty. [differences] 293}	Elo: 23.73 ±1.3 _{Ptnml: 27, 4314, 17265, 8329, 65 nElo: 52.00 ±2.8 PairsRatio: 1.93 [raw statistics]}	Elo: 22.88 ±1.2 _{Ptnml: 4, 3365, 19325, 7293, 13 nElo: 55.40 ±2.8 PairsRatio: 2.17 [raw statistics]}
2025‑05‑25	master vs Stockfish 17 _{Bench: 2312696 Simplify Double Margin Formula [differences] 322}	Elo: 23.31 ±1.3 _{Ptnml: 18, 4401, 17161, 8384, 36 nElo: 51.06 ±2.8 PairsRatio: 1.91 [raw statistics]}	Elo: 20.91 ±1.2 _{Ptnml: 4, 3528, 19330, 7133, 5 nElo: 50.50 ±2.8 PairsRatio: 2.02 [raw statistics]}
2025‑06‑02	master vs Stockfish 17 _{Bench: 2307268 remove non-functional else [differences] 340}	Elo: 26.57 ±1.3 _{Ptnml: 19, 4125, 17163, 8644, 49 nElo: 58.46 ±2.9 PairsRatio: 2.10 [raw statistics]}	Elo: 20.96 ±1.1 _{Ptnml: 7, 3461, 19450, 7074, 8 nElo: 50.87 ±2.8 PairsRatio: 2.04 [raw statistics]}
2025‑07‑24	master vs Stockfish 17 _{Bench: 2759840 Simplify eval >= beta condition from NMP [differences] 362}	Elo: 25.39 ±1.3 _{Ptnml: 19, 4190, 17248, 8481, 62 nElo: 55.85 ±2.8 PairsRatio: 2.03 [raw statistics]}	Elo: 20.42 ±1.1 _{Ptnml: 4, 3505, 19464, 7019, 8 nElo: 49.56 ±2.8 PairsRatio: 2.00 [raw statistics]}
2025‑07‑28	master vs Stockfish 17 _{Bench: 2902492 Simplify LMR extension limit formula [differences] 373}	Elo: 18.36 ±1.3 _{Ptnml: 44, 4840, 17087, 7963, 66 nElo: 39.54 ±2.8 PairsRatio: 1.64 [raw statistics]}	Elo: 22.32 ±1.2 _{Ptnml: 6, 3424, 19293, 7269, 8 nElo: 53.91 ±2.8 PairsRatio: 2.12 [raw statistics]}
2025‑08‑04	master vs Stockfish 17 _{Bench: 2946135 Only set ep square if ep capture is possible [differences] 388}	Elo: 24.28 ±1.3 _{Ptnml: 27, 4273, 17248, 8390, 62 nElo: 53.26 ±2.8 PairsRatio: 1.97 [raw statistics]}	Elo: 22.05 ±1.2 _{Ptnml: 6, 3455, 19281, 7246, 12 nElo: 53.17 ±2.8 PairsRatio: 2.10 [raw statistics]}
2025‑08‑17	master vs Stockfish 17 _{Bench: 2130122 VVLTC tweak [differences] 405}	Elo: 20.44 ±1.3 _{Ptnml: 30, 4582, 17262, 8085, 41 nElo: 44.65 ±2.8 PairsRatio: 1.76 [raw statistics]}	Elo: 18.61 ±1.2 _{Ptnml: 11, 3695, 19377, 6907, 10 nElo: 44.77 ±2.8 PairsRatio: 1.87 [raw statistics]}
2025‑08‑24	master vs Stockfish 17 _{Bench: 2693376 Simplify LMR Extensions [differences] 419}	Elo: 19.43 ±1.3 _{Ptnml: 15, 4584, 17480, 7876, 45 nElo: 42.83 ±2.8 PairsRatio: 1.72 [raw statistics]}	Elo: 20.62 ±1.2 _{Ptnml: 5, 3564, 19310, 7112, 9 nElo: 49.67 ±2.8 PairsRatio: 2.00 [raw statistics]}
2025‑09‑02	master vs Stockfish 17 _{Bench: 2667107 Add scaling note to STC/LTC tunes [differences] 434}	Elo: 22.43 ±1.3 _{Ptnml: 23, 4380, 17364, 8172, 61 nElo: 49.29 ±2.8 PairsRatio: 1.87 [raw statistics]}	Elo: 19.97 ±1.2 _{Ptnml: 6, 3594, 19364, 7021, 15 nElo: 48.14 ±2.8 PairsRatio: 1.95 [raw statistics]}
2025‑09‑28	master vs Stockfish 17 _{Bench: 2515619 Simplify use of low-ply history in evasions [differences] 450}	Elo: 24.61 ±1.3 _{Ptnml: 12, 4343, 17087, 8506, 52 nElo: 53.82 ±2.8 PairsRatio: 1.97 [raw statistics]}	Elo: 22.46 ±1.2 _{Ptnml: 4, 3451, 19226, 7306, 13 nElo: 54.06 ±2.8 PairsRatio: 2.12 [raw statistics]}
2025‑10‑14	master vs Stockfish 17 _{Bench: 2343840 Use huge pages for worker data [differences] 464}	Elo: 29.31 ±1.3 _{Ptnml: 22, 3941, 17067, 8906, 64 nElo: 64.47 ±2.9 PairsRatio: 2.26 [raw statistics]}	Elo: 26.56 ±1.2 _{Ptnml: 6, 3179, 19058, 7745, 12 nElo: 63.99 ±2.8 PairsRatio: 2.44 [raw statistics]}

Version Comparison

Elo Progression

Normalized Elo Progression

Game Pair Ratio Progression

30 Day Average

Draw Percentage vs Elo

Historical Information

Stockfish 3 Development (2013-03-01 - 2013-04-30)

`Date`	`Version`	`1 Thread`
2013‑03‑04	master vs Stockfish 2.3.1 _{Bench: 4968764 Increase see prune depth [differences] 226}	Elo: 15.00 ±2.8 _{WDL: 2906, 13325, 3769 nElo: 26.02 ±4.8 [raw statistics]}
2013‑03‑11	master vs Stockfish 2.3.1 _{Bench: 4968764 Be more aggressive on trying to finish iterations [differences] 227}	Elo: 15.49 ±2.8 _{WDL: 3016, 13077, 3907 nElo: 26.38 ±4.8 [raw statistics]}
2013‑03‑11	master vs Stockfish 2.3.1 _{Bench: 4968764 Check for easy move just once [differences] 228}	Elo: 13.42 ±2.8 _{WDL: 2974, 13280, 3746 nElo: 23.19 ±4.8 [raw statistics]}
2013‑03‑16	master vs Stockfish 2.3.1 _{Bench: 5442365 Further increase SEE prune depth [differences] 232}	Elo: 17.77 ±2.8 _{WDL: 2897, 13184, 3919 nElo: 30.53 ±4.8 [raw statistics]}
2013‑03‑24	master vs Stockfish 2.3.1 _{Bench: 4985829 Update bestValue when futility pruning (2) [differences] 237}	Elo: 16.71 ±2.8 _{WDL: 2874, 13291, 3835 nElo: 28.92 ±4.8 [raw statistics]}
2013‑03‑30	master vs Stockfish 2.3.1 _{Bench: 4781239 Set IID half way between d/2 and d-4 [differences] 241}	Elo: 18.76 ±2.8 _{WDL: 2824, 13273, 3903 nElo: 32.46 ±4.8 [raw statistics]}
2013‑04‑03	master vs Stockfish 2.3.1 _{Bench: 4705335 Double Impact of Gain tables [differences] 242}	Elo: 15.44 ±2.8 _{WDL: 3040, 13032, 3928 nElo: 26.21 ±4.8 [raw statistics]}
2013‑04‑06	master vs Stockfish 2.3.1 _{Bench: 4361224 Increase null verification threshold to 12 plies [differences] 249}	Elo: 17.11 ±2.8 _{WDL: 2774, 12861, 3727 nElo: 29.62 ±4.9 [raw statistics]}
2013‑04‑07	master vs Stockfish 2.3.1 _{Bench: 5473339 Rescale UCI parameters to 100 [differences] 252}	Elo: 19.02 ±2.8 _{WDL: 2948, 13010, 4042 nElo: 32.29 ±4.8 [raw statistics]}
2013‑04‑10	master vs Stockfish 2.3.1 _{Bench: 5157061 De-templetize Position::is_draw() [differences] 257}	Elo: 24.13 ±2.8 _{WDL: 2791, 13031, 4178 nElo: 41.10 ±4.8 [raw statistics]}
2013‑04‑19	master vs Stockfish 2.3.1 _{Bench: 5274705 Skip a couple of popcount in previous patch [differences] 262}	Elo: 28.27 ±2.9 _{WDL: 2754, 12868, 4378 nElo: 47.69 ±4.9 [raw statistics]}
2013‑04‑26	master vs Stockfish 2.3.1 _{Bench: 4311634 Fix a crash introduced few days ago [differences] 270}	Elo: 33.67 ±2.9 _{WDL: 2642, 12784, 4574 nElo: 56.61 ±4.9 [raw statistics]}
2013‑04‑28	master vs Stockfish 2.3.1 _{Bench: 4176431 Temporary revert "Expose EvalInfo struct to search" [differences] 273}	Elo: 30.86 ±2.9 _{WDL: 2721, 12786, 4493 nElo: 51.82 ±4.9 [raw statistics]}
2013‑04‑30	Stockfish 3 _{Bench: 4176431 [differences] 275}

Stockfish 4 Development (2013-04-30 - 2013-08-20)

`Date`	`Version`	`1 Thread`
2013‑05‑16	master vs Stockfish 3 _{Bench: 4327405 Use two counter moves instead of one [differences] 28}	Elo: 22.11 ±3.0 _{WDL: 3212, 12305, 4483 nElo: 35.78 ±4.8 [raw statistics]}
2013‑05‑23	master vs Stockfish 3 _{Bench: 4821467 Bunch of 3 small patches [differences] 33}	Elo: 26.70 ±2.1 _{WDL: 6435, 24062, 9503 nElo: 42.53 ±3.4 [raw statistics]}
2013‑05‑31	master vs Stockfish 3 _{Bench: 4931544 Passed pawn tuning [differences] 38}	Elo: 29.50 ±2.2 _{WDL: 6588, 23436, 9976 nElo: 46.13 ±3.4 [raw statistics]}
2013‑06‑23	master vs Stockfish 3 _{Bench: 4609948 Fix some stale comments [differences] 72}	Elo: 35.47 ±2.2 _{WDL: 6196, 23539, 10265 nElo: 55.80 ±3.4 [raw statistics]}
2013‑07‑03	master vs Stockfish 3 _{Bench: 4507288 Simplify aspiration window code [differences] 88}	Elo: 37.36 ±2.2 _{WDL: 6223, 23269, 10508 nElo: 58.35 ±3.4 [raw statistics]}
2013‑07‑13	master vs Stockfish 3 _{Bench: 4558173 Fully qualify memset and memcpy [differences] 100}	Elo: 39.27 ±3.1 _{WDL: 3052, 11645, 5303 nElo: 61.44 ±4.9 [raw statistics]}
2013‑07‑19	master vs Stockfish 3 _{Bench: 4769737 Halve king eval margin [differences] 110}	Elo: 39.83 ±3.1 _{WDL: 3067, 11583, 5350 nElo: 62.10 ±4.9 [raw statistics]}
2013‑07‑25	master vs Stockfish 3 _{Bench: 4727133 Rewrite pawn shield and storm code [differences] 133}	Elo: 48.84 ±3.3 _{WDL: 3203, 10801, 5996 nElo: 73.11 ±4.9 [raw statistics]}
2013‑08‑03	master vs Stockfish 3 _{Bench: 4424151 Streamline time computation [differences] 147}	Elo: 50.95 ±3.2 _{WDL: 3056, 10976, 5968 nElo: 77.14 ±4.9 [raw statistics]}
2013‑08‑18	master vs Stockfish 3 _{Bench: 4132374 Further tweak movecount pruning [differences] 162}	Elo: 56.66 ±3.3 _{WDL: 2988, 10791, 6221 nElo: 85.22 ±5.0 [raw statistics]}
2013‑08‑20	Stockfish 4 _{Bench: 4132374 [differences] 165}

Stockfish DD Development (2013-08-20 - 2013-11-29)

`Date`	`Version`	`1 Thread`
2013‑08‑29	master vs Stockfish 4 _{Bench: 4620975 Enable LMR for dangerous moves [differences] 12}	Elo: 16.18 ±2.9 _{WDL: 3221, 12627, 4152 nElo: 26.72 ±4.8 [raw statistics]}
2013‑09‑01	master vs Stockfish 4 _{Bench: 3453945 Don't use lpthread for Android [differences] 18}	Elo: 19.30 ±2.9 _{WDL: 3083, 12724, 4193 nElo: 32.11 ±4.8 [raw statistics]}
2013‑09‑05	master vs Stockfish 4 _{Bench: 4633330 Do not prune useless checks in QS [differences] 23}	Elo: 23.80 ±2.9 _{WDL: 2932, 12768, 4300 nElo: 39.78 ±4.8 [raw statistics]}
2013‑09‑07	master vs Stockfish 4 _{Bench: 3864419 Remove unreachable values in mobility table [differences] 27}	Elo: 27.66 ±2.9 _{WDL: 2766, 12879, 4355 nElo: 46.68 ±4.9 [raw statistics]}
2013‑09‑11	master vs Stockfish 4 _{Bench: 4554576 Extend checks more when below alpha [differences] 35}	Elo: 24.87 ±2.9 _{WDL: 2824, 12923, 4253 nElo: 42.04 ±4.8 [raw statistics]}
2013‑09‑12	master vs Stockfish 4 _{Bench: 4554579 Revert "Move draw by material check" [differences] 37}	Elo: 24.34 ±2.9 _{WDL: 2825, 12951, 4224 nElo: 41.22 ±4.8 [raw statistics]}
2013‑09‑13	master vs Stockfish 4 _{Bench: 3846852 Increase passed bonus for having more pieces [differences] 38}	Elo: 26.21 ±2.9 _{WDL: 2871, 12752, 4377 nElo: 43.80 ±4.8 [raw statistics]}
2013‑09‑16	master vs Stockfish 4 _{Bench: 3884003 Fix time parameters for blitz games [differences] 47}	Elo: 31.56 ±2.1 _{WDL: 5588, 25200, 9212 nElo: 52.33 ±3.4 [raw statistics]}
2013‑09‑23	master vs Stockfish 4 _{Bench: 3529630 Update disabled warnings for Intel compiler [differences] 54}	Elo: 34.03 ±2.1 _{WDL: 5449, 25197, 9354 nElo: 56.49 ±3.4 [raw statistics]}
2013‑09‑28	master vs Stockfish 4 _{Bench: 3172206 Drop 'is' prefix from query functions [differences] 62}	Elo: 33.49 ±2.9 _{WDL: 2571, 12936, 4493 nElo: 56.93 ±4.9 [raw statistics]}
2013‑09‑29	master vs Stockfish 4 _{Bench: 8336338 Add more depth/positions to bench [differences] 63}	Elo: 33.90 ±2.0 _{WDL: 5292, 25525, 9183 nElo: 56.93 ±3.4 [raw statistics]}
2013‑10‑08	master vs Stockfish 4 _{Bench: 8340585 Use TT refined value to stand pat [differences] 66}	Elo: 36.58 ±2.9 _{WDL: 2623, 12656, 4721 nElo: 61.07 ±4.9 [raw statistics]}
2013‑10‑08	master vs Stockfish 4 _{Bench: 8340585 Increase slowmover and reduce instability [differences] 67}	Elo: 38.91 ±2.1 _{WDL: 5102, 25335, 9563 nElo: 65.11 ±3.5 [raw statistics]}
2013‑10‑09	master vs Stockfish 4 _{Bench: 8279065 Smoother transition for LMR [differences] 68}	Elo: 39.29 ±2.1 _{WDL: 5071, 25354, 9575 nElo: 65.80 ±3.4 [raw statistics]}
2013‑10‑14	master vs Stockfish 4 _{Bench: 7700683 Double king safety weights [differences] 75}	Elo: 43.64 ±2.9 _{WDL: 2432, 12637, 4931 nElo: 73.12 ±4.9 [raw statistics]}
2013‑10‑18	master vs Stockfish 4 _{Bench: 8440524 Score chain pawn also by rank [differences] 78}	Elo: 49.51 ±2.1 _{WDL: 4821, 24696, 10483 nElo: 81.68 ±3.5 [raw statistics]}
2013‑10‑19	master vs Stockfish 4 _{Bench: 9160831 Further increase safe checks bonus [differences] 80}	Elo: 50.11 ±2.1 _{WDL: 4817, 24636, 10547 nElo: 82.54 ±3.5 [raw statistics]}
2013‑10‑20	master vs Stockfish 4 _{Bench: 9294116 Further improve chain pawn evaluation [differences] 84}	Elo: 49.72 ±3.1 _{WDL: 2677, 11803, 5520 nElo: 79.12 ±4.9 [raw statistics]}
2013‑10‑22	master vs Stockfish 4 _{Bench: 8455956 Tweak again chain pawn bonus [differences] 87}	Elo: 53.85 ±3.0 _{WDL: 2425, 12075, 5500 nElo: 87.51 ±4.9 [raw statistics]}
2013‑10‑24	master vs Stockfish 4 _{Bench: 8291883 Retire mirror() [differences] 94}	Elo: 55.18 ±3.0 _{WDL: 2385, 12080, 5535 nElo: 89.82 ±4.9 [raw statistics]}
2013‑10‑28	master vs Stockfish 4 _{Bench: 8029334 Tweak bishop pair and knight weight [differences] 96}	Elo: 52.84 ±2.1 _{WDL: 4866, 24231, 10903 nElo: 86.04 ±3.5 [raw statistics]}
2013‑11‑01	master vs Stockfish 4 _{Bench: 7995098 Set timer to a fixed interval [differences] 98}	Elo: 59.73 ±3.0 _{WDL: 2324, 11947, 5729 nElo: 96.77 ±5.0 [raw statistics]}
2013‑11‑09	master vs Stockfish 4 _{Bench: 7243575 Futility pruning simplification [differences] 106}	Elo: 60.68 ±3.0 _{WDL: 2198, 12146, 5656 nElo: 99.73 ±5.0 [raw statistics]}
2013‑11‑10	master vs Stockfish 4 _{Bench: 9282549 Remove opposed flag for doubled pawns [differences] 113}	Elo: 61.23 ±2.1 _{WDL: 4333, 24357, 11310 nElo: 100.91 ±3.5 [raw statistics]}
2013‑11‑11	master vs Stockfish 4 _{Bench: 8331357 Simplify generate<EVASIONS> [differences] 116}	Elo: 63.85 ±2.1 _{WDL: 4185, 24361, 11454 nElo: 105.53 ±3.5 [raw statistics]}
2013‑11‑29	master vs Stockfish 4 _{Bench: 8596156 Add support for PPC 64bit on Linux [differences] 123}	Elo: 67.44 ±2.1 _{WDL: 4119, 24094, 11787 nElo: 110.87 ±3.5 [raw statistics]}
2013‑11‑29	Stockfish DD _{Bench: 8596156 [differences] 124}

Stockfish 5 Development (2013-11-29 - 2014-05-31)

`Date`	`Version`	`1 Thread`
2013‑12‑09	master vs Stockfish DD _{Bench: 7869223 Research at intermediate depth if LMR is very high [differences] 23}	Elo: 7.94 ±1.9 _{WDL: 5662, 27762, 6576 nElo: 14.37 ±3.4 [raw statistics]}
2013‑12‑19	master vs Stockfish DD _{Bench: 7425809 Faster and simplified threat eval [differences] 29}	Elo: 11.35 ±1.9 _{WDL: 5766, 27162, 7072 nElo: 20.06 ±3.4 [raw statistics]}
2013‑12‑23	master vs Stockfish DD _{Bench: 6835416 Loosened trigger condition for king safety [differences] 31}	Elo: 18.62 ±2.0 _{WDL: 5619, 26620, 7761 nElo: 32.31 ±3.4 [raw statistics]}
2013‑12‑29	master vs Stockfish DD _{Bench: 7762310 Retire asymmThreshold [differences] 36}	Elo: 19.54 ±2.0 _{WDL: 5580, 26593, 7827 nElo: 33.87 ±3.4 [raw statistics]}
2014‑01‑02	master vs Stockfish DD _{Bench: 7602383 Ensure move_importance() is non-zero [differences] 46}	Elo: 25.36 ±2.0 _{WDL: 5371, 26343, 8286 nElo: 43.67 ±3.4 [raw statistics]}
2014‑01‑08	master vs Stockfish DD _{Bench: 8502826 Position::gives_check - use ci.ksq [differences] 55}	Elo: 29.85 ±2.0 _{WDL: 5165, 26242, 8593 nElo: 51.32 ±3.4 [raw statistics]}
2014‑01‑14	master vs Stockfish DD _{Bench: 7205153 Introduce 'follow up' moves [differences] 59}	Elo: 29.84 ±2.0 _{WDL: 5222, 26129, 8649 nElo: 51.09 ±3.4 [raw statistics]}
2014‑01‑19	master vs Stockfish DD _{Bench: 7804908 Small simplification to Position::see [differences] 64}	Elo: 32.49 ±2.0 _{WDL: 5088, 26094, 8818 nElo: 55.65 ±3.4 [raw statistics]}
2014‑01‑29	master vs Stockfish DD _{Bench: 6875743 Tweak bishop PSQT tables [differences] 70}	Elo: 36.66 ±2.0 _{WDL: 4905, 25985, 9110 nElo: 62.70 ±3.4 [raw statistics]}
2014‑02‑09	master vs Stockfish DD _{Bench: 8347121 Faster handling of king captures in Position::see [differences] 79}	Elo: 38.63 ±2.0 _{WDL: 4956, 25659, 9385 nElo: 65.38 ±3.4 [raw statistics]}
2014‑02‑22	master vs Stockfish DD _{Bench: 8430785 Fix a warning with Intel compiler [differences] 99}	Elo: 38.93 ±2.0 _{WDL: 4944, 25649, 9407 nElo: 65.87 ±3.4 [raw statistics]}
2014‑02‑26	master vs Stockfish DD _{Bench: 7990513 Dynamic draw value [differences] 100}	Elo: 39.25 ±2.1 _{WDL: 5164, 25172, 9664 nElo: 65.32 ±3.4 [raw statistics]}
2014‑03‑14	master vs Stockfish DD _{Bench: 7451319 Depth dependent aspiration window delta [differences] 122}	Elo: 40.85 ±2.0 _{WDL: 4925, 25469, 9606 nElo: 68.77 ±3.5 [raw statistics]}
2014‑03‑24	master vs Stockfish DD _{Bench: 7682173 Simplify TT replace strategy [differences] 138}	Elo: 43.70 ±2.1 _{WDL: 4887, 25221, 9892 nElo: 73.08 ±3.5 [raw statistics]}
2014‑04‑08	master vs Stockfish DD _{Bench: 7533692 Restrict queen mobility to safe squares [differences] 159}	Elo: 47.70 ±2.1 _{WDL: 4689, 25165, 10146 nElo: 79.86 ±3.5 [raw statistics]}
2014‑04‑12	master vs Stockfish DD _{Bench: 6921356 Move args parsing to UCI::loop [differences] 174}	Elo: 49.21 ±2.1 _{WDL: 4717, 24938, 10345 nElo: 81.84 ±3.5 [raw statistics]}
2014‑04‑21	master vs Stockfish DD _{Bench: 7384368 Reset DrawValue[] before new search [differences] 184}	Elo: 54.53 ±2.1 _{WDL: 4742, 24289, 10969 nElo: 89.09 ±3.5 [raw statistics]}
2014‑04‑25	master vs Stockfish DD _{Bench: 7905850 Speed up picking of killers [differences] 191}	Elo: 57.08 ±2.2 _{WDL: 4858, 23771, 11371 nElo: 91.87 ±3.5 [raw statistics]}
2014‑05‑04	master vs Stockfish DD _{Bench: 8802105 Revert dynamic contempt [differences] 216}	Elo: 53.27 ±2.2 _{WDL: 5183, 23549, 11268 nElo: 84.84 ±3.5 [raw statistics]}
2014‑05‑13	master vs Stockfish DD _{Bench: 8739659 Drop to qsearch at low depth in razoring [differences] 227}	Elo: 57.15 ±1.8 _{WDL: 7289, 35641, 17070 nElo: 91.95 ±2.9 [raw statistics]}
2014‑05‑17	master vs Stockfish DD _{Bench: 8732553 Fix an off-by-one bug in extract_pv_from_tt [differences] 229}	Elo: 55.26 ±2.2 _{WDL: 5108, 23475, 11417 nElo: 87.95 ±3.5 [raw statistics]}
2014‑05‑24	master vs Stockfish DD _{Bench: 7396783 Fix a warning with Intel compiler [differences] 234}	Elo: 53.28 ±2.1 _{WDL: 4858, 24198, 10944 nElo: 86.68 ±3.5 [raw statistics]}
2014‑05‑31	Stockfish 5 _{Bench: 8732553 [differences] 236}

Stockfish 6 Development (2014-05-31 - 2015-01-27)

`Date`	`Version`	`1 Thread`
2014‑06‑03	master vs Stockfish 5 _{Bench: 8205159 Symmetric King Safety: take 2 [differences] 8}	Elo: 5.35 ±1.8 _{WDL: 5386, 28612, 6002 nElo: 10.03 ±3.4 [raw statistics]}
2014‑06‑11	master vs Stockfish 5 _{Bench: 7875814 Simplify pawn threats and merge into ThreatenedByPawn[] [differences] 22}	Elo: 8.30 ±2.0 _{WDL: 4589, 24491, 5413 nElo: 15.43 ±3.7 [raw statistics]}
2014‑06‑29	master vs Stockfish 5 _{Bench: 8759675 Fix Singular extension condition to handle mate scores [differences] 46}	Elo: 10.78 ±1.8 _{WDL: 5152, 28455, 6393 nElo: 20.10 ±3.4 [raw statistics]}
2014‑07‑22	master vs Stockfish 5 _{Bench: 7831429 Outpost tuning [differences] 62}	Elo: 19.63 ±1.8 _{WDL: 4775, 28192, 7033 nElo: 36.29 ±3.4 [raw statistics]}
2014‑08‑06	master vs Stockfish 5 _{Bench: 7461881 Remove insufficient material rule [differences] 73}	Elo: 19.68 ±1.8 _{WDL: 4737, 28263, 7000 nElo: 36.49 ±3.4 [raw statistics]}
2014‑09‑04	master vs Stockfish 5 _{Bench: 7461881 Small tweak to idle_loop() [differences] 82}	Elo: 15.90 ±1.8 _{WDL: 4986, 28199, 6815 nElo: 29.35 ±3.4 [raw statistics]}
2014‑09‑27	master vs Stockfish 5 _{Bench: 6545733 Remove use of half-ply reductions [differences] 93}	Elo: 22.80 ±1.9 _{WDL: 4664, 28051, 7285 nElo: 41.96 ±3.4 [raw statistics]}
2014‑10‑15	master vs Stockfish 5 _{Bench: 7328585 Document why initing eval tables [differences] 108}	Elo: 27.58 ±1.9 _{WDL: 4613, 27605, 7782 nElo: 49.96 ±3.4 [raw statistics]}
2014‑11‑01	master vs Stockfish 5 _{Bench: 6564212 Merge pull request #89 from official-stockfish/pull_no_pretty [differences] 129}	Elo: 31.00 ±1.9 _{WDL: 4484, 27472, 8044 nElo: 55.96 ±3.4 [raw statistics]}
2014‑11‑10	master vs Stockfish 5 _{Bench: 6807896 Profile Build with Hash=16 [differences] 148}	Elo: 36.21 ±1.9 _{WDL: 4357, 27132, 8511 nElo: 64.71 ±3.4 [raw statistics]}
2014‑11‑25	master vs Stockfish 5 _{Bench: 8255966 Bitbase index() from ADD to OR [differences] 168}	Elo: 39.02 ±1.9 _{WDL: 4151, 27225, 8624 nElo: 70.14 ±3.4 [raw statistics]}
2014‑12‑07	master vs Stockfish 5 _{Bench: 9324905 Simpler PRNG and faster magics search [differences] 181}	Elo: 41.42 ±1.9 _{WDL: 4108, 27038, 8854 nElo: 74.04 ±3.4 [raw statistics]}
2014‑12‑22	master vs Stockfish 5 _{Bench: 9498821 Prefer names to numbers in storm code [differences] 197}	Elo: 46.26 ±1.9 _{WDL: 4011, 26683, 9306 nElo: 81.89 ±3.4 [raw statistics]}
2015‑01‑07	master vs Stockfish 5 _{Bench: 7604776 Assorted formatting and comment tweaks in position.h [differences] 213}	Elo: 52.10 ±2.0 _{WDL: 3913, 26688, 9948 nElo: 91.46 ±3.4 [raw statistics]}
2015‑01‑18	master vs Stockfish 5 _{Bench: 8080602 Stockfish 6 Release Candidate 1 [differences] 228}	Elo: 51.71 ±1.9 _{WDL: 3723, 26644, 9633 nElo: 91.89 ±3.5 [raw statistics]}
2015‑01‑27	Stockfish 6 _{Bench: 8918745 [differences] 236}

Stockfish 7 Development (2015-01-27 - 2016-01-02)

`Date`	`Version`	`1 Thread`
2015‑02‑08	master vs Stockfish 6 _{Bench: 7699138 Pawn Center Bind Bonus [differences] 12}	Elo: 7.50 ±2.0 _{WDL: 6423, 26291, 7286 nElo: 12.81 ±3.4 [raw statistics]}
2015‑03‑19	master vs Stockfish 6 _{Bench: 8226843 Retire ConditionVariable [differences] 123}	Elo: 15.92 ±1.8 _{WDL: 4796, 28576, 6628 nElo: 29.89 ±3.4 [raw statistics]}
2015‑03‑29	master vs Stockfish 6 _{Bench: 7658627 Remove some difficult to understand C++11 constructs [differences] 137}	Elo: 19.02 ±1.8 _{WDL: 4590, 28633, 6777 nElo: 35.82 ±3.4 [raw statistics]}
2015‑04‑10	master vs Stockfish 6 _{Bench: 6985247 Allow Position::init() to be called more than once [differences] 151}	Elo: 22.12 ±1.8 _{WDL: 4480, 28497, 7023 nElo: 41.48 ±3.4 [raw statistics]}
2015‑05‑09	master vs Stockfish 6 _{Bench: 8787152 Smart TT save [differences] 164}	Elo: 28.82 ±1.8 _{WDL: 4197, 28295, 7508 nElo: 53.80 ±3.4 [raw statistics]}
2015‑06‑07	master vs Stockfish 6 _{Bench: 6716940 Simplify outpost evaluation [differences] 176}	Elo: 27.85 ±1.9 _{WDL: 4501, 27798, 7701 nElo: 50.86 ±3.4 [raw statistics]}
2015‑07‑16	master vs Stockfish 6 _{Bench: 6943812 Fix formatting of previous patch [differences] 187}	Elo: 30.74 ±1.9 _{WDL: 4367, 27736, 7897 nElo: 56.09 ±3.4 [raw statistics]}
2015‑07‑30	master vs Stockfish 6 _{Bench: 8040572 Simplify IID depth formula [differences] 192}	Elo: 34.04 ±1.9 _{WDL: 4283, 27527, 8190 nElo: 61.72 ±3.4 [raw statistics]}
2015‑10‑03	master vs Stockfish 6 _{Bench: 8073614 File based passed pawn bonus [differences] 214}	Elo: 44.23 ±1.9 _{WDL: 3690, 27555, 8755 nElo: 80.99 ±3.4 [raw statistics]}
2015‑10‑25	master vs Stockfish 6 _{Bench: 8004751 Use atomics instead of volatile [differences] 232}	Elo: 61.76 ±1.9 _{WDL: 3197, 26570, 10233 nElo: 110.69 ±3.5 [raw statistics]}
2015‑12‑27	master vs Stockfish 6 _{Bench: 8355485 Stockfish 7 Beta 1 [differences] 267}	Elo: 62.62 ±1.6 _{WDL: 4472, 40358, 15170 nElo: 113.94 ±2.8 [raw statistics]}
2016‑01‑02	Stockfish 7 _{Bench: 8355485 [differences] 273}

Stockfish 8 Development (2016-01-02 - 2016-11-01)

`Date`	`Version`	`1 Thread`
2016‑01‑28	master vs Stockfish 7 _{Bench: 7751425 Time management simplification [differences] 16}	Elo: 4.93 ±1.5 _{WDL: 3814, 31804, 4382 nElo: 10.90 ±3.4 [raw statistics]}
2016‑03‑10	master vs Stockfish 7 _{Bench: 8261839 Add follow up moves history for move ordering [differences] 28}	Elo: 12.83 ±1.5 _{WDL: 3354, 31816, 4830 nElo: 28.44 ±3.4 [raw statistics]}
2016‑04‑08	master vs Stockfish 7 _{Bench: 7482426 Small passed pawn simplification [differences] 42}	Elo: 15.27 ±1.5 _{WDL: 3251, 31741, 5008 nElo: 33.74 ±3.4 [raw statistics]}
2016‑05‑20	master vs Stockfish 7 _{Bench: 8428997 More detailed dependence of time allocation [differences] 64}	Elo: 29.44 ±1.6 _{WDL: 2719, 31217, 6104 nElo: 63.61 ±3.4 [raw statistics]}
2016‑06‑10	master vs Stockfish 7 _{Bench: 8276130 Stat Formula Tweak [differences] 76}	Elo: 36.29 ±1.6 _{WDL: 2606, 30625, 6769 nElo: 76.48 ±3.4 [raw statistics]}
2016‑07‑24	master vs Stockfish 7 _{Bench: 8145304 Allow null pruning at depth 1 [differences] 94}	Elo: 49.73 ±1.7 _{WDL: 2415, 29483, 8102 nElo: 100.27 ±3.4 [raw statistics]}
2016‑08‑18	master vs Stockfish 7 _{Bench: 7662861 Remove a stale assignment [differences] 101}	Elo: 52.59 ±1.7 _{WDL: 2413, 29165, 8422 nElo: 104.74 ±3.4 [raw statistics]}
2016‑09‑07	master vs Stockfish 7 _{Bench: 6024713 Refactor previous patch [differences] 124}	Elo: 66.53 ±1.8 _{WDL: 1893, 28647, 9460 nElo: 131.97 ±3.3 [raw statistics]}
2016‑10‑07	master vs Stockfish 7 _{Bench: 6421663 Optimisation of Position::see and Position::see_sign [differences] 149}	Elo: 76.60 ±1.8 _{WDL: 1571, 28179, 10250 nElo: 151.24 ±3.3 [raw statistics]}
2016‑11‑01	Stockfish 8 _{Bench: 5926706 [differences] 168}

Stockfish 9 Development (2016-11-01 - 2018-01-31)

`Date`	`Version`	`1 Thread`
2016‑12‑31	master vs Stockfish 8 _{Bench: 5468995 Small eval cleanup and renaming [differences] 55}	Elo: 5.21 ±1.5 _{WDL: 3656, 32088, 4256 nElo: 11.72 ±3.4 [raw statistics]}
2017‑01‑29	master vs Stockfish 8 _{Bench: 5941174 Simplify TT penalty stat (#980) [differences] 86}	Elo: 8.82 ±1.5 _{WDL: 3580, 31825, 4595 nElo: 19.53 ±3.4 [raw statistics]}
2017‑03‑08	master vs Stockfish 8 _{Bench: 5803228 Helper functions to count material for both sides [differences] 106}	Elo: 10.84 ±1.6 _{WDL: 3569, 31614, 4817 nElo: 23.73 ±3.4 [raw statistics]}
2017‑04‑20	master vs Stockfish 8 _{Bench: 6581936 simplify logic for history based pruning [differences] 127}	Elo: 15.17 ±1.6 _{WDL: 3430, 31395, 5175 nElo: 32.82 ±3.4 [raw statistics]}
2017‑05‑07	master vs Stockfish 8 _{Bench: 6107863 Linear Protector bonus by distance [differences] 144}	Elo: 20.25 ±1.6 _{WDL: 3258, 31155, 5587 nElo: 43.35 ±3.4 [raw statistics]}
2017‑06‑21	master vs Stockfish 8 _{Bench: 5725676 Increase reduction if tt-move is a capture [differences] 167}	Elo: 27.41 ±1.6 _{WDL: 2918, 31015, 6067 nElo: 58.52 ±3.4 [raw statistics]}
2017‑08‑26	master vs Stockfish 8 _{Bench: 5965302 Improve multi-threaded mate finding [differences] 218}	Elo: 29.32 ±1.6 _{WDL: 2886, 30860, 6254 nElo: 62.17 ±3.4 [raw statistics]}
2017‑10‑02	master vs Stockfish 8 _{Bench: 5620312 Good bishops on the main diagonals [differences] 237}	Elo: 32.61 ±1.6 _{WDL: 2688, 30881, 6431 nElo: 69.44 ±3.4 [raw statistics]}
2017‑11‑03	master vs Stockfish 8 _{Bench: 5536775 Introduce capture history table for capture move sorting [differences] 247}	Elo: 35.18 ±1.6 _{WDL: 2682, 30600, 6718 nElo: 73.93 ±3.4 [raw statistics]}
2017‑12‑03	master vs Stockfish 8 _{Bench: 5051254 Use constexpr when makes sense [differences] 261}	Elo: 43.31 ±1.7 _{WDL: 2406, 30227, 7367 nElo: 90.06 ±3.3 [raw statistics]}
2018‑01‑23	master vs Stockfish 8 _{Bench: 5783344 Contempt 20 [differences] 286}	Elo: 57.25 ±1.9 _{WDL: 2917, 27634, 9449 nElo: 106.75 ±3.4 [raw statistics]}
2018‑01‑31	Stockfish 9 _{Bench: 5023629 [differences] 291}

Stockfish 10 Development (2018-01-31 - 2018-11-29)

`Date`	`Version`	`1 Thread`
2018‑02‑28	master vs Stockfish 9 _{Bench: 5765806 Reintroduce depth 2 razoring (with additional margin) [differences] 41}	Elo: 5.16 ±1.7 _{WDL: 5143, 30105, 5752 nElo: 10.02 ±3.4 [raw statistics]}
2018‑03‑07	master vs Stockfish 9 _{Bench: 5544908 Simplification: use Arctan for the optimism S-curve [differences] 53}	Elo: 6.94 ±1.7 _{WDL: 4813, 29575, 5612 nElo: 13.60 ±3.4 [raw statistics]}
2018‑03‑13	master vs Stockfish 9 _{Bench: 5741807 Use intrinsics only for LSB/MSB [differences] 64}	Elo: 13.03 ±1.7 _{WDL: 4463, 29574, 5963 nElo: 25.59 ±3.4 [raw statistics]}
2018‑03‑26	master vs Stockfish 9 _{Bench: 5934103 Make kingRing always 8 squares [differences] 75}	Elo: 13.77 ±1.7 _{WDL: 4339, 29737, 5924 nElo: 27.26 ±3.4 [raw statistics]}
2018‑04‑03	master vs Stockfish 9 _{Bench: 4989125 Remove the Queen from the mobility area of minor pieces [differences] 92}	Elo: 16.59 ±1.7 _{WDL: 4283, 29525, 6192 nElo: 32.54 ±3.4 [raw statistics]}
2018‑04‑07	master vs Stockfish 9 _{Bench: 5170165 Reset negative statScore on fail high [differences] 94}	Elo: 16.63 ±1.8 _{WDL: 4397, 29293, 6310 nElo: 32.25 ±3.4 [raw statistics]}
2018‑04‑23	master vs Stockfish 9 _{Bench: 5549801 Alternative formula for dynamic contempt [differences] 106}	Elo: 15.90 ±1.8 _{WDL: 4462, 29247, 6291 nElo: 30.76 ±3.4 [raw statistics]}
2018‑04‑29	master vs Stockfish 9 _{Bench: 5254862 Always scale using pawn contribution [differences] 112}	Elo: 14.61 ±1.7 _{WDL: 4430, 29459, 6111 nElo: 28.54 ±3.4 [raw statistics]}
2018‑05‑03	master vs Stockfish 9 _{Bench: 5186783 Tweak the connected[] array value for pawns on rank 5 [differences] 116}	Elo: 18.52 ±1.8 _{WDL: 4385, 29100, 6515 nElo: 35.63 ±3.4 [raw statistics]}
2018‑05‑13	master vs Stockfish 9 _{Bench: 5294316 Update search.cpp [differences] 128}	Elo: 24.92 ±1.8 _{WDL: 4175, 28786, 7039 nElo: 47.42 ±3.4 [raw statistics]}
2018‑05‑24	master vs Stockfish 9 _{Bench: 5167159 LMR Capture Tweak [differences] 137}	Elo: 26.72 ±1.8 _{WDL: 4033, 28864, 7103 nElo: 51.08 ±3.4 [raw statistics]}
2018‑06‑05	master vs Stockfish 9 _{Bench: 4326784 Call cycle detection before qsearch() [differences] 148}	Elo: 28.16 ±1.8 _{WDL: 3971, 28823, 7206 nElo: 53.79 ±3.4 [raw statistics]}
2018‑06‑11	master vs Stockfish 9 _{Bench: 4980482 Optimize an expression in endgame.cpp [differences] 154}	Elo: 29.72 ±1.9 _{WDL: 4335, 27917, 7748 nElo: 54.60 ±3.4 [raw statistics]}
2018‑06‑23	master vs Stockfish 9 _{Bench: 4557946 Another set of tuned values after one million games [differences] 162}	Elo: 31.98 ±1.9 _{WDL: 4354, 27621, 8025 nElo: 58.11 ±3.4 [raw statistics]}
2018‑07‑19	master vs Stockfish 9 _{Bench: 4817583 Better check evasion move sorting [differences] 179}	Elo: 36.70 ±1.9 _{WDL: 4312, 27166, 8522 nElo: 65.70 ±3.4 [raw statistics]}
2018‑07‑27	master vs Stockfish 9 _{Bench: 4905530 Simplify cmh pruning [differences] 199}	Elo: 37.45 ±1.9 _{WDL: 4183, 27339, 8478 nElo: 67.55 ±3.4 [raw statistics]}
2018‑07‑28	master vs Stockfish 9 _{Bench: 4883742 Increase the mg->eg gradient for the PawnlessFlank malus [differences] 200}	Elo: 35.84 ±1.9 _{WDL: 4235, 27418, 8347 nElo: 64.78 ±3.4 [raw statistics]}
2018‑07‑31	master vs Stockfish 9 _{Bench: 5591925 Small tweaks to recent code changes [differences] 203}	Elo: 37.67 ±1.9 _{WDL: 4019, 27642, 8339 nElo: 68.82 ±3.4 [raw statistics]}
2018‑08‑08	master vs Stockfish 9 _{Bench: 4669050 First check threshold in space evaluation [differences] 207}	Elo: 37.78 ±1.9 _{WDL: 4224, 27220, 8556 nElo: 67.82 ±3.4 [raw statistics]}
2018‑08‑12	master vs Stockfish 9 _{Bench: 4694813 Combo of several promising parameter tweaks [differences] 211}	Elo: 40.88 ±1.9 _{WDL: 4069, 27177, 8754 nElo: 73.46 ±3.4 [raw statistics]}
2018‑08‑14	master vs Stockfish 9 _{Bench: 4272361 Double weight of capture history [differences] 214}	Elo: 41.69 ±1.9 _{WDL: 3942, 27339, 8719 nElo: 75.47 ±3.4 [raw statistics]}
2018‑08‑17	master vs Stockfish 9 _{Bench: 4592766 Use an affine formula to mix stats and eval [differences] 217}	Elo: 43.15 ±1.9 _{WDL: 3922, 27213, 8865 nElo: 77.82 ±3.4 [raw statistics]}
2018‑08‑28	master vs Stockfish 9 _{Bench: 4172767 Tweak stat bonus formula [differences] 220}	Elo: 44.20 ±1.9 _{WDL: 3861, 27217, 8922 nElo: 79.79 ±3.4 [raw statistics]}
2018‑08‑28	master vs Stockfish 9 _{Bench: 4413173 Remove PawnsOnBothFlanks [differences] 225}	Elo: 42.37 ±1.9 _{WDL: 3952, 27242, 8806 nElo: 76.44 ±3.4 [raw statistics]}
2018‑09‑01	master vs Stockfish 9 _{Bench: 4609645 Re-introduce "keep pawns on both flanks" [differences] 227}	Elo: 46.46 ±1.9 _{WDL: 3804, 27075, 9121 nElo: 83.56 ±3.4 [raw statistics]}
2018‑09‑10	master vs Stockfish 9 _{Bench: 4248710 Tweak opposite colored bishops endgame scaling [differences] 230}	Elo: 45.47 ±1.9 _{WDL: 3911, 26973, 9116 nElo: 81.36 ±3.4 [raw statistics]}
2018‑09‑27	master vs Stockfish 9 _{Bench: 4059356 Fix two typos in comments [differences] 235}	Elo: 46.93 ±1.9 _{WDL: 3883, 26864, 9253 nElo: 83.72 ±3.4 [raw statistics]}
2018‑10‑14	master vs Stockfish 9 _{Bench: 4274207 Simplify check extensions [differences] 241}	Elo: 49.01 ±1.9 _{WDL: 3783, 26829, 9388 nElo: 87.49 ±3.4 [raw statistics]}
2018‑10‑25	master vs Stockfish 9 _{Bench: 3314347 On main thread: reduce depth after fail high [differences] 245}	Elo: 52.82 ±1.9 _{WDL: 3514, 26937, 9549 nElo: 95.10 ±3.4 [raw statistics]}
2018‑11‑01	master vs Stockfish 9 _{Bench: 3556672 Fix issues from using adjustedDepth too broadly [differences] 248}	Elo: 51.68 ±1.9 _{WDL: 3581, 26932, 9487 nElo: 92.90 ±3.4 [raw statistics]}
2018‑11‑08	master vs Stockfish 9 _{Bench: 3647775 Update list of top CPU contributors [differences] 254}	Elo: 50.43 ±1.9 _{WDL: 3773, 26689, 9538 nElo: 89.65 ±3.5 [raw statistics]}
2018‑11‑19	master vs Stockfish 9 _{Bench: 3717396 Stockfish 10-beta [differences] 267}	Elo: 53.77 ±1.9 _{WDL: 3612, 26634, 9754 nElo: 95.73 ±3.5 [raw statistics]}
2018‑11‑27	master vs Stockfish 9 _{Bench: 3939338 Simplify casting extension [differences] 274}	Elo: 54.21 ±1.9 _{WDL: 3562, 26685, 9753 nElo: 96.75 ±3.5 [raw statistics]}
2018‑11‑29	Stockfish 10 _{Bench: 3939338 [differences] 277}

Stockfish 11 Development (2018-11-29 - 2020-01-17)

`Date`	`Version`	`1 Thread`	`8 Threads`
2018‑12‑06	master vs Stockfish 10 _{Bench: 3773021 Revert "pseudo_legal() and MOVE_NONE" [differences] 8}	Elo: 4.32 ±1.7 _{WDL: 5033, 29437, 5530 nElo: 8.40 ±3.4 [raw statistics]}
2018‑12‑13	master vs Stockfish 10 _{Bench: 3332460 A combo of parameter tweaks [differences] 16}	Elo: 8.06 ±1.8 _{WDL: 5020, 29032, 5948 nElo: 15.41 ±3.4 [raw statistics]}	Elo: 12.70 ±1.7 _{WDL: 4068, 30403, 5529 nElo: 25.98 ±3.4 [raw statistics]}
2018‑12‑16	master vs Stockfish 10 _{Bench: 3646542 Use stronglyProtected [differences] 21}	Elo: 7.85 ±1.7 _{WDL: 5107, 30004, 6037 nElo: 15.10 ±3.4 [raw statistics]}
2019‑01‑04	master vs Stockfish 10 _{Bench: 3559104 Check tablebase files [differences] 40}	Elo: 7.20 ±1.8 _{WDL: 5164, 28843, 5993 nElo: 13.64 ±3.4 [raw statistics]}
2019‑01‑10	master vs Stockfish 10 _{Bench: 3739723 Remove pvExact [differences] 45}	Elo: 13.14 ±1.8 _{WDL: 4779, 28930, 6291 nElo: 25.03 ±3.4 [raw statistics]}	Elo: 16.17 ±1.7 _{WDL: 3887, 30366, 5747 nElo: 33.07 ±3.4 [raw statistics]}
2019‑01‑22	master vs Stockfish 10 _{Bench: 3665090 Simplify TrappedRook [differences] 53}	Elo: 13.98 ±1.8 _{WDL: 4714, 28963, 6323 nElo: 26.68 ±3.4 [raw statistics]}
2019‑02‑03	master vs Stockfish 10 _{Bench: 3653942 Less king danger if we have a knight [differences] 61}	Elo: 17.71 ±1.8 _{WDL: 4624, 28715, 6661 nElo: 33.46 ±3.4 [raw statistics]}	Elo: 19.77 ±1.7 _{WDL: 3728, 30270, 6002 nElo: 40.32 ±3.4 [raw statistics]}
2019‑03‑12	master vs Stockfish 10 _{Bench: 3318033 Increase thread stack for OS X (#2035) [differences] 80}	Elo: 16.58 ±1.8 _{WDL: 4635, 28823, 6542 nElo: 31.46 ±3.4 [raw statistics]}
2019‑03‑31	master vs Stockfish 10 _{Bench: 3548313 Assorted trivial cleanups 3/2019 (#2030) [differences] 91}	Elo: 16.58 ±1.8 _{WDL: 4742, 28609, 6649 nElo: 31.16 ±3.4 [raw statistics]}	Elo: 24.33 ±1.7 _{WDL: 3633, 29937, 6430 nElo: 48.91 ±3.4 [raw statistics]}
2019‑04‑24	master vs Stockfish 10 _{Bench: 3402947 Remove useless initializations (#2115) [differences] 113}	Elo: 16.39 ±1.8 _{WDL: 4634, 28847, 6519 nElo: 31.13 ±3.4 [raw statistics]}
2019‑05‑05	master vs Stockfish 10 _{Bench: 3644175 LMR for captures not cracking alpha [differences] 121}	Elo: 16.65 ±1.8 _{WDL: 4788, 28508, 6704 nElo: 31.17 ±3.4 [raw statistics]}
2019‑05‑15	master vs Stockfish 10 _{Bench: 3824325 Update failedHighCnt rule #2063 [differences] 136}	Elo: 19.76 ±1.8 _{WDL: 4665, 28397, 6938 nElo: 36.86 ±3.4 [raw statistics]}	Elo: 28.93 ±1.7 _{WDL: 3573, 29531, 6896 nElo: 57.18 ±3.4 [raw statistics]}
2019‑06‑09	master vs Stockfish 10 _{Bench: 3424592 Remove depth condition for ttPv (#2166) [differences] 151}	Elo: 19.87 ±1.9 _{WDL: 4796, 28123, 7081 nElo: 36.62 ±3.4 [raw statistics]}
2019‑06‑20	master vs Stockfish 10 _{Bench: 3398333 More bonus for free passed pawn [differences] 161}	Elo: 24.06 ±1.8 _{WDL: 4547, 28140, 7313 nElo: 44.48 ±3.4 [raw statistics]}	Elo: 30.76 ±1.7 _{WDL: 3462, 29544, 6994 nElo: 60.92 ±3.4 [raw statistics]}
2019‑06‑27	master vs Stockfish 10 _{Bench: 3633546 Bonus for double attacks [differences] 167}	Elo: 22.75 ±1.9 _{WDL: 4644, 28096, 7260 nElo: 41.95 ±3.4 [raw statistics]}
2019‑07‑11	master vs Stockfish 10 _{Bench: 3206912 Assorted trivial cleanups June 2019 [differences] 176}	Elo: 24.39 ±1.9 _{WDL: 4596, 28005, 7399 nElo: 44.83 ±3.4 [raw statistics]}
2019‑07‑25	master vs Stockfish 10 _{Bench: 3935523 Tweak of SEE pruning condition [differences] 192}	Elo: 25.72 ±1.9 _{WDL: 4519, 28006, 7475 nElo: 47.32 ±3.4 [raw statistics]}	Elo: 37.49 ±1.7 _{WDL: 3225, 29251, 7524 nElo: 73.63 ±3.4 [raw statistics]}
2019‑08‑14	master vs Stockfish 10 _{Bench: 4139590 Tweak unsafe checks [differences] 198}	Elo: 32.24 ±1.9 _{WDL: 4168, 27963, 7869 nElo: 59.45 ±3.4 [raw statistics]}
2019‑08‑26	master vs Stockfish 10 _{Bench: 3568210 Tweak Late Move Reduction at root [differences] 207}	Elo: 35.63 ±1.9 _{WDL: 4021, 27870, 8109 nElo: 65.62 ±3.4 [raw statistics]}	Elo: 44.52 ±1.8 _{WDL: 2958, 28986, 8056 nElo: 86.99 ±3.4 [raw statistics]}
2019‑09‑12	master vs Stockfish 10 _{Bench: 3954190 Scale down complexity [differences] 211}	Elo: 39.10 ±1.9 _{WDL: 3824, 27869, 8307 nElo: 72.22 ±3.4 [raw statistics]}
2019‑09‑16	master vs Stockfish 10 _{Bench: 4272173 Raise stack size to 8MB for pthreads [differences] 218}	Elo: 37.63 ±1.9 _{WDL: 4007, 27670, 8323 nElo: 68.83 ±3.4 [raw statistics]}	Elo: 46.57 ±1.8 _{WDL: 2764, 28492, 7994 nElo: 91.44 ±3.4 [raw statistics]}
2019‑09‑24	master vs Stockfish 10 _{Bench: 3618154 Increase weight for supported pawns [differences] 226}	Elo: 38.97 ±1.9 _{WDL: 3857, 27818, 8325 nElo: 71.81 ±3.4 [raw statistics]}
2019‑10‑05	master vs Stockfish 10 _{Bench: 4131643 Introduce separate counter-move tables [differences] 239}	Elo: 41.96 ±1.9 _{WDL: 3746, 27701, 8553 nElo: 77.13 ±3.4 [raw statistics]}	Elo: 51.76 ±1.8 _{WDL: 2628, 28829, 8543 nElo: 101.26 ±3.4 [raw statistics]}
2019‑10‑18	master vs Stockfish 10 _{Bench: 4423737 Current capture for Counter-Move history [differences] 247}	Elo: 44.63 ±1.9 _{WDL: 3641, 27608, 8751 nElo: 81.93 ±3.4 [raw statistics]}
2019‑11‑04	master vs Stockfish 10 _{Bench: 4707799 Rook PSQT Tuned [differences] 259}	Elo: 42.20 ±1.9 _{WDL: 3686, 27793, 8521 nElo: 77.91 ±3.4 [raw statistics]}	Elo: 52.90 ±1.8 _{WDL: 2601, 28754, 8645 nElo: 103.29 ±3.4 [raw statistics]}
2019‑11‑14	master vs Stockfish 10 _{Bench: 4532366 Prune before extension [differences] 266}	Elo: 43.12 ±1.9 _{WDL: 3676, 27709, 8615 nElo: 79.39 ±3.4 [raw statistics]}
2019‑11‑21	master vs Stockfish 10 _{Bench: 5067870 Do lmr for more captures [differences] 271}	Elo: 46.56 ±1.5 _{WDL: 5306, 41395, 13299 nElo: 85.60 ±2.8 [raw statistics]}	Elo: 53.93 ±1.8 _{WDL: 2502, 28837, 8661 nElo: 105.86 ±3.4 [raw statistics]}
2019‑12‑02	master vs Stockfish 10 _{Bench: 5122362 UnblockedStorm tuned [differences] 278}	Elo: 44.88 ±1.5 _{WDL: 5273, 41746, 12981 nElo: 83.21 ±2.8 [raw statistics]}
2019‑12‑10	master vs Stockfish 10 _{Bench: 5371271 Refine improving-logic [differences] 288}	Elo: 47.27 ±1.5 _{WDL: 5329, 41229, 13442 nElo: 86.56 ±2.8 [raw statistics]}	Elo: 56.62 ±1.8 _{WDL: 2365, 28809, 8826 nElo: 111.42 ±3.4 [raw statistics]}
2020‑01‑07	master vs Stockfish 10 _{Bench: 4747984 Tuned nullmove search [differences] 294}	Elo: 51.50 ±1.5 _{Ptnml: 160, 3173, 15729, 9546, 1387 nElo: 98.05 ±2.8 PairsRatio: 3.28 [raw statistics]}	Elo: 58.15 ±1.7 _{Ptnml: 36, 1527, 11059, 6509, 860 nElo: 118.69 ±3.4 PairsRatio: 4.71 [raw statistics]}
2020‑01‑17	master vs Stockfish 10 _{Bench: 5156767 Stockfish 11 [differences] 307}	Elo: 53.59 ±1.5 _{Ptnml: 138, 2988, 15833, 9631, 1407 nElo: 102.99 ±2.8 PairsRatio: 3.53 [raw statistics]}	Elo: 58.07 ±1.7 _{Ptnml: 36, 1478, 11159, 6463, 854 nElo: 119.25 ±3.4 PairsRatio: 4.83 [raw statistics]}
2020‑01‑17	Stockfish 11 _{Bench: 5156767 [differences] 307}

Stockfish 12 Development (2020-01-17 - 2020-09-02)

`Date`	`Version`	`1 Thread`	`8 Threads`
2020‑01‑28	master vs Stockfish 11 _{Bench: 5545845 More bonus for bestMoves [differences] 16}	Elo: -2.47 ±1.3 _{Ptnml: 330, 5657, 18424, 5285, 303 nElo: -5.21 ±2.8 PairsRatio: 0.93 [raw statistics]}
2020‑01‑31	master vs Stockfish 11 _{Bench: 5153165 Revert 5 recent patches [differences] 19}	Elo: 0.85 ±1.3 _{Ptnml: 306, 5327, 18593, 5457, 314 nElo: 1.80 ±2.8 PairsRatio: 1.02 [raw statistics]}
2020‑02‑27	master vs Stockfish 11 _{Bench: 4923286 Weak queen protection [differences] 32}	Elo: 1.33 ±1.3 _{Ptnml: 327, 5308, 18486, 5567, 312 nElo: 2.80 ±2.8 PairsRatio: 1.04 [raw statistics]}	Elo: 0.51 ±1.4 _{Ptnml: 118, 3072, 13560, 3133, 117 nElo: 1.21 ±3.4 PairsRatio: 1.02 [raw statistics]}
2020‑03‑20	master vs Stockfish 11 _{Bench: 5398277 Adjust singular extension search depth [differences] 48}	Elo: 2.94 ±1.3 _{Ptnml: 351, 5099, 18580, 5631, 339 nElo: 6.21 ±2.8 PairsRatio: 1.10 [raw statistics]}
2020‑04‑07	master vs Stockfish 11 _{Bench: 4417023 Introduce capture history pruning [differences] 63}	Elo: 5.74 ±1.3 _{Ptnml: 274, 5058, 18460, 5818, 390 nElo: 12.11 ±2.8 PairsRatio: 1.16 [raw statistics]}	Elo: 6.49 ±1.5 _{Ptnml: 113, 2854, 13369, 3501, 163 nElo: 15.05 ±3.4 PairsRatio: 1.23 [raw statistics]}
2020‑04‑16	master vs Stockfish 11 _{Bench: 4958027 Remove one condition in probcut TTmove [differences] 76}	Elo: 11.33 ±1.3 _{Ptnml: 281, 4681, 18282, 6313, 443 nElo: 23.65 ±2.8 PairsRatio: 1.36 [raw statistics]}
2020‑05‑02	master vs Stockfish 11 _{Bench: 4247490 Fishtest Tuning Framework [differences] 84}	Elo: 15.21 ±1.3 _{Ptnml: 236, 4370, 18388, 6545, 461 nElo: 32.08 ±2.8 PairsRatio: 1.52 [raw statistics]}	Elo: 16.71 ±1.5 _{Ptnml: 105, 2457, 13100, 4087, 251 nElo: 37.85 ±3.4 PairsRatio: 1.69 [raw statistics]}
2020‑05‑21	master vs Stockfish 11 _{Bench: 4778956 Tweak knight mobility [differences] 100}	Elo: 15.97 ±1.3 _{Ptnml: 230, 4544, 17963, 6766, 497 nElo: 33.08 ±2.8 PairsRatio: 1.52 [raw statistics]}
2020‑06‑06	master vs Stockfish 11 _{Bench: 4582693 Use lowply-history also on low depths [differences] 117}	Elo: 19.45 ±1.4 _{Ptnml: 250, 4360, 17761, 7042, 587 nElo: 39.70 ±2.8 PairsRatio: 1.65 [raw statistics]}	Elo: 23.70 ±1.5 _{Ptnml: 88, 2142, 12987, 4524, 259 nElo: 53.99 ±3.4 PairsRatio: 2.14 [raw statistics]}
2020‑06‑13	master vs Stockfish 11 _{Bench: 4246971 Tuned values for search constants [differences] 127}	Elo: 20.91 ±1.4 _{Ptnml: 195, 4263, 17878, 7069, 595 nElo: 43.14 ±2.8 PairsRatio: 1.72 [raw statistics]}	Elo: 24.86 ±1.5 _{Ptnml: 81, 2088, 13016, 4523, 292 nElo: 56.58 ±3.4 PairsRatio: 2.22 [raw statistics]}
2020‑06‑29	master vs Stockfish 11 _{Bench: 4523573 Tweak single queen endgame scaling [differences] 148}	Elo: 25.67 ±1.3 _{Ptnml: 192, 3878, 17888, 7397, 645 nElo: 53.10 ±2.8 PairsRatio: 1.98 [raw statistics]}
2020‑07‑17	master vs Stockfish 11 _{Bench: 4578298 Do not overwrite valuable TT data [differences] 163}	Elo: 26.44 ±1.3 _{Ptnml: 192, 3800, 17928, 7418, 662 nElo: 54.75 ±2.8 PairsRatio: 2.02 [raw statistics]}	Elo: 30.71 ±1.5 _{Ptnml: 63, 1923, 12759, 4935, 320 nElo: 69.50 ±3.4 PairsRatio: 2.65 [raw statistics]}
2020‑07‑31	master vs Stockfish 11 _{Bench: 4746616 Tweak cutnode reduction [differences] 167}	Elo: 25.49 ±1.4 _{Ptnml: 203, 3910, 17861, 7342, 684 nElo: 52.38 ±2.8 PairsRatio: 1.95 [raw statistics]}	Elo: 32.39 ±1.5 _{Ptnml: 69, 1829, 12779, 4961, 362 nElo: 73.03 ±3.4 PairsRatio: 2.80 [raw statistics]}
2020‑08‑06	master vs Stockfish 11 _{Bench: 4746616 Add NNUE evaluation [differences] 168}	Elo: 83.42 ±1.7 _{Ptnml: 172, 2656, 12724, 11761, 2687 nElo: 144.72 ±3.0 PairsRatio: 5.11 [raw statistics]}	Elo: 86.10 ±1.9 _{Ptnml: 36, 1192, 9342, 7881, 1549 nElo: 163.20 ±3.6 PairsRatio: 7.68 [raw statistics]}
2020‑08‑07	Add NNUE evaluation _{Bench: 4746616 [differences] 168}
2020‑08‑08	master vs Stockfish 11 _{Bench: 4084753 LMR search tweak [differences] 185}	Elo: 106.20 ±1.7 _{Ptnml: 67, 1716, 11867, 13060, 3290 nElo: 189.91 ±3.2 PairsRatio: 9.17 [raw statistics]}
2020‑08‑11	master vs Stockfish 11 _{Bench: 4290577 This commit enables a mixed bench [differences] 205}	Elo: 125.60 ±1.7 _{Ptnml: 48, 1240, 10613, 14070, 4029 nElo: 224.82 ±3.3 PairsRatio: 14.05 [raw statistics]}	Elo: 111.78 ±1.9 _{Ptnml: 11, 591, 8286, 9168, 1944 nElo: 217.93 ±3.8 PairsRatio: 18.46 [raw statistics]}
2020‑08‑18	master vs Stockfish 11 _{Bench: 4026216 Fix Makefile typo [differences] 226}	Elo: 121.54 ±1.7 _{Ptnml: 52, 1373, 10930, 13640, 4005 nElo: 215.22 ±3.3 PairsRatio: 12.38 [raw statistics]}	Elo: 111.40 ±1.9 _{Ptnml: 20, 700, 8128, 9161, 1991 nElo: 213.20 ±3.8 PairsRatio: 15.49 [raw statistics]}
2020‑08‑30	master vs Stockfish 11 _{Bench: 3736029 Update parameters in classical evaluation [differences] 255}	Elo: 130.96 ±1.7 _{Ptnml: 44, 1161, 10305, 14128, 4362 nElo: 232.58 ±3.4 PairsRatio: 15.34 [raw statistics]}
2020‑09‑02	master vs Stockfish 11 _{Bench: 3624569 Stockfish 12 [differences] 262}	Elo: 133.65 ±1.7 _{Ptnml: 32, 1088, 10158, 14286, 4436 nElo: 238.67 ±3.4 PairsRatio: 16.72 [raw statistics]}	Elo: 117.62 ±1.9 _{Ptnml: 10, 562, 8016, 9195, 2217 nElo: 224.93 ±3.8 PairsRatio: 19.95 [raw statistics]}
2020‑09‑02	Stockfish 12 _{Bench: 3624569 [differences] 262}

Stockfish 13 Development (2020-09-02 - 2021-02-18)

`Date`	`Version`	`1 Thread`	`8 Threads`
2020‑09‑08	master vs Stockfish 12 _{Bench: 4161067 Double probability of using classical eval [differences] 10}	Elo: 6.49 ±1.0 _{Ptnml: 85, 3319, 22112, 4359, 125 nElo: 17.26 ±2.8 PairsRatio: 1.32 [raw statistics]}
2020‑09‑21	master vs Stockfish 12 _{Bench: 3973739 Add large page support for NNUE weights [differences] 21}	Elo: 13.88 ±1.0 _{Ptnml: 49, 2767, 22106, 4896, 182 nElo: 37.07 ±2.8 PairsRatio: 1.80 [raw statistics]}	Elo: 8.97 ±1.1 _{Ptnml: 15, 1474, 16020, 2445, 46 nElo: 27.99 ±3.4 PairsRatio: 1.67 [raw statistics]}
2020‑09‑28	master vs Stockfish 12 _{Bench: 3776081 Include pawns in NNUE scaling [differences] 33}	Elo: 23.15 ±1.0 _{Ptnml: 38, 1945, 22217, 5587, 213 nElo: 63.29 ±2.7 PairsRatio: 2.92 [raw statistics]}
2020‑10‑18	master vs Stockfish 12 _{Bench: 4066972 Do more reductions for late quiet moves [differences] 41}	Elo: 24.09 ±1.0 _{Ptnml: 43, 2023, 21889, 5827, 218 nElo: 64.60 ±2.7 PairsRatio: 2.93 [raw statistics]}	Elo: 21.17 ±1.1 _{Ptnml: 12, 908, 15789, 3216, 75 nElo: 65.43 ±3.2 PairsRatio: 3.58 [raw statistics]}
2020‑11‑01	master vs Stockfish 12 _{Bench: 3517795 Update default net to nn-cb26f10b1fd9.nnue [differences] 48}	Elo: 28.02 ±1.1 _{Ptnml: 63, 2079, 21107, 6469, 282 nElo: 71.59 ±2.7 PairsRatio: 3.15 [raw statistics]}
2020‑11‑15	master vs Stockfish 12 _{Bench: 3597730 Rook Mobility Tweak [differences] 60}	Elo: 29.99 ±1.0 _{Ptnml: 32, 1667, 21658, 6389, 254 nElo: 80.38 ±2.7 PairsRatio: 3.91 [raw statistics]}	Elo: 25.49 ±1.1 _{Ptnml: 10, 799, 15532, 3570, 89 nElo: 77.27 ±3.2 PairsRatio: 4.52 [raw statistics]}
2020‑11‑29	master vs Stockfish 12 _{Bench: 3561701 Update default net to nn-62ef826d1a6d.nnue [differences] 72}	Elo: 30.61 ±1.0 _{Ptnml: 19, 1645, 21655, 6407, 274 nElo: 82.09 ±2.7 PairsRatio: 4.02 [raw statistics]}
2020‑12‑14	master vs Stockfish 12 _{Bench: 4050630 Increase reduction in case of stable best move [differences] 79}	Elo: 32.09 ±1.0 _{Ptnml: 33, 1581, 21474, 6651, 261 nElo: 85.57 ±2.7 PairsRatio: 4.28 [raw statistics]}	Elo: 27.50 ±1.1 _{Ptnml: 10, 706, 15480, 3723, 81 nElo: 83.75 ±3.1 PairsRatio: 5.31 [raw statistics]}
2020‑12‑31	master vs Stockfish 12 _{Bench: 4109336 WeakUnopposed penalty for backwards [differences] 89}	Elo: 33.71 ±1.0 _{Ptnml: 23, 1475, 21475, 6730, 297 nElo: 90.01 ±2.6 PairsRatio: 4.69 [raw statistics]}
2021‑01‑13	master vs Stockfish 12 _{Bench: 4287509 Optimize generate_moves [differences] 101}	Elo: 32.40 ±1.0 _{Ptnml: 31, 1487, 21588, 6660, 234 nElo: 87.55 ±2.7 PairsRatio: 4.54 [raw statistics]}	Elo: 28.29 ±1.1 _{Ptnml: 10, 671, 15468, 3761, 90 nElo: 86.06 ±3.1 PairsRatio: 5.65 [raw statistics]}
2021‑02‑15	master vs Stockfish 12 _{Bench: 3766422 Small trivial clean-ups, February 2021 [differences] 121}	Elo: 36.03 ±1.1 _{Ptnml: 29, 1395, 21210, 7079, 287 nElo: 95.63 ±2.7 PairsRatio: 5.17 [raw statistics]}	Elo: 29.08 ±1.1 _{Ptnml: 6, 626, 15476, 3806, 86 nElo: 89.08 ±3.1 PairsRatio: 6.16 [raw statistics]}
2021‑02‑18	Stockfish 13 _{Bench: 3766422 [differences] 123}

Stockfish 14 Development (2021-02-18 - 2021-07-02)

`Date`	`Version`	`1 Thread`	`8 Threads`
2021‑02‑26	master vs Stockfish 13 _{Bench: 5037279 Introduce DistanceFromPV [differences] 4}	Elo: 1.34 ±0.8 _{Ptnml: 28, 2367, 24980, 2596, 29 nElo: 4.55 ±2.8 PairsRatio: 1.10 [raw statistics]}
2021‑03‑24	master vs Stockfish 13 _{Bench: 4339126 Small cleanups (march 2021) [differences] 18}	Elo: 0.61 ±0.8 _{Ptnml: 18, 2457, 24938, 2575, 12 nElo: 2.09 ±2.8 PairsRatio: 1.05 [raw statistics]}
2021‑04‑15	master vs Stockfish 13 _{Bench: 4503918 Use classical eval for Bishop vs Pawns [differences] 29}	Elo: 1.47 ±0.8 _{Ptnml: 39, 2384, 24886, 2667, 24 nElo: 4.93 ±2.8 PairsRatio: 1.11 [raw statistics]}	Elo: 0.89 ±0.9 _{Ptnml: 11, 1279, 17318, 1381, 11 nElo: 3.38 ±3.4 PairsRatio: 1.08 [raw statistics]}
2021‑05‑22	master vs Stockfish 13 _{Bench: 3856635 Sometimes change the balance [differences] 62}	Elo: 10.12 ±1.0 _{Ptnml: 60, 2454, 23277, 4096, 113 nElo: 29.34 ±2.8 PairsRatio: 1.67 [raw statistics]}
2021‑06‑14	master vs Stockfish 13 _{Bench: 4877339 Update default net to nn-8e47cf062333.nnue [differences] 90}	Elo: 21.80 ±1.1 _{Ptnml: 67, 2216, 21852, 5620, 245 nElo: 57.47 ±2.7 PairsRatio: 2.57 [raw statistics]}	Elo: 16.96 ±1.1 _{Ptnml: 15, 1083, 15923, 2894, 85 nElo: 52.38 ±3.3 PairsRatio: 2.71 [raw statistics]}
2021‑06‑18	master vs Stockfish 13 _{Bench: 4900906 Make net nn-50144f835024.nnue the default [differences] 100}	Elo: 25.56 ±1.0 _{Ptnml: 30, 1814, 22084, 5864, 208 nElo: 69.95 ±2.7 PairsRatio: 3.29 [raw statistics]}
2021‑06‑29	master vs Stockfish 13 _{Bench: 4770936 Update Top CPU Contributors [differences] 113}	Elo: 30.27 ±1.0 _{Ptnml: 14, 1443, 22127, 6146, 270 nElo: 83.66 ±2.6 PairsRatio: 4.40 [raw statistics]}	Elo: 22.62 ±1.1 _{Ptnml: 7, 755, 15977, 3153, 108 nElo: 71.15 ±3.1 PairsRatio: 4.28 [raw statistics]}
2021‑07‑02	Stockfish 14 _{Bench: 4770936 [differences] 114}

Stockfish 15 Development (2021-07-02 - 2022-04-18)

`Date`	`Version`	`1 Thread`	`8 Threads`	`1 Thread (UHO)`
2021‑07‑26	master vs Stockfish 14 _{Bench: 5124774 Update default net to nn-26abeed38351.nnue [differences] 17}	Elo: 2.74 ±0.8 _{Ptnml: 24, 2000, 25476, 2478, 22 nElo: 9.85 ±2.8 PairsRatio: 1.24 [raw statistics]}
2021‑08‑15	master vs Stockfish 14 _{Bench: 5189338 New NNUE architecture and net [differences] 26}	Elo: 9.31 ±0.9 _{Ptnml: 24, 2044, 24321, 3522, 89 nElo: 29.61 ±2.7 PairsRatio: 1.75 [raw statistics]}	Elo: 6.08 ±0.9 _{Ptnml: 5, 1063, 17183, 1725, 24 nElo: 22.66 ±3.4 PairsRatio: 1.64 [raw statistics]}
2021‑08‑31	master vs Stockfish 14 _{Bench: 5600615 Update default net to nn-735bba95dec0.nnue [differences] 39}	Elo: 15.04 ±0.9 _{Ptnml: 17, 1601, 24272, 3990, 120 nElo: 47.86 ±2.7 PairsRatio: 2.54 [raw statistics]}
2021‑09‑15	master vs Stockfish 14 _{Bench: 6658747 Update default net to nn-13406b1dcbe0.nnue [differences] 46}	Elo: 16.64 ±0.9 _{Ptnml: 21, 1878, 23452, 4506, 143 nElo: 49.53 ±2.7 PairsRatio: 2.45 [raw statistics]}	Elo: 12.39 ±0.9 _{Ptnml: 1, 766, 17084, 2104, 45 nElo: 45.59 ±3.2 PairsRatio: 2.80 [raw statistics]}
2021‑10‑06	master vs Stockfish 14 _{Bench: 6261865 Capping stat bonus at 2000 [differences] 57}	Elo: 18.68 ±0.9 _{Ptnml: 28, 1496, 23821, 4535, 120 nElo: 57.70 ±2.7 PairsRatio: 3.05 [raw statistics]}	Elo: 11.74 ±0.9 _{Ptnml: 4, 769, 17137, 2052, 38 nElo: 43.60 ±3.2 PairsRatio: 2.70 [raw statistics]}
2021‑10‑18	master vs Stockfish 14 _{Bench: 5005810 Simplify probCutCount away [differences] 67}	Elo: 17.69 ±0.9 _{Ptnml: 13, 1577, 23891, 4382, 137 nElo: 54.78 ±2.7 PairsRatio: 2.84 [raw statistics]}
2021‑10‑23	master vs Stockfish 14 _{Bench: 6334068 Adjust ButterflyHistory decay parameter [differences] 78}	Elo: 17.87 ±0.9 _{Ptnml: 11, 1377, 24244, 4253, 115 nElo: 57.35 ±2.6 PairsRatio: 3.15 [raw statistics]}	Elo: 10.27 ±0.9 _{Ptnml: 3, 696, 17438, 1842, 21 nElo: 40.55 ±3.2 PairsRatio: 2.67 [raw statistics]}
2021‑10‑28	Stockfish 14.1 _{Bench: 6334068 [differences] 80}
2021‑11‑05	master vs Stockfish 14 _{Bench: 6719976 Tweak initial aspiration window [differences] 89}	Elo: 18.71 ±0.9 _{Ptnml: 16, 1293, 24255, 4319, 117 nElo: 60.14 ±2.6 PairsRatio: 3.39 [raw statistics]}
2021‑11‑23	master vs Stockfish 14 _{Bench: 7334766 Less futility pruning [differences] 98}	Elo: 19.35 ±0.9 _{Ptnml: 19, 1405, 23923, 4524, 129 nElo: 60.39 ±2.6 PairsRatio: 3.27 [raw statistics]}	Elo: 13.28 ±0.9 _{Ptnml: 3, 696, 17112, 2148, 41 nElo: 49.26 ±3.2 PairsRatio: 3.13 [raw statistics]}
2021‑11‑28	master vs Stockfish 14 _{Bench: 6302543 Refine futility pruning for parent nodes [differences] 103}	Elo: 24.44 ±0.9 _{Ptnml: 9, 1054, 23776, 5037, 124 nElo: 76.95 ±2.5 PairsRatio: 4.86 [raw statistics]}
2021‑12‑07	master vs Stockfish 14 _{Bench: 4667742 Update default net to nn-63376713ba63.nnue [differences] 118}	Elo: 26.99 ±0.9 _{Ptnml: 11, 998, 23473, 5365, 153 nElo: 83.13 ±2.5 PairsRatio: 5.47 [raw statistics]}	Elo: 17.80 ±0.9 _{Ptnml: 6, 529, 16919, 2504, 42 nElo: 64.76 ±3.1 PairsRatio: 4.76 [raw statistics]}
2021‑12‑14	master vs Stockfish 14 _{Bench: 4735679 Remove NNUE scaling term [differences] 126}	Elo: 26.45 ±0.9 _{Ptnml: 9, 962, 23656, 5207, 166 nElo: 82.28 ±2.5 PairsRatio: 5.53 [raw statistics]}
2021‑12‑22	master vs Stockfish 14 _{Bench: 4633875 Update default net to nn-ac07bd334b62.nnue [differences] 139}	Elo: 28.65 ±0.9 _{Ptnml: 11, 1036, 23172, 5567, 214 nElo: 85.61 ±2.5 PairsRatio: 5.52 [raw statistics]}	Elo: 17.66 ±0.9 _{Ptnml: 2, 520, 16976, 2448, 54 nElo: 64.60 ±3.0 PairsRatio: 4.79 [raw statistics]}
2022‑01‑10	master vs Stockfish 14 _{Bench: 4572746 Adjust pruning constants [differences] 148}	Elo: 30.51 ±1.0 _{Ptnml: 13, 1065, 22809, 5879, 234 nElo: 89.03 ±2.5 PairsRatio: 5.67 [raw statistics]}
2022‑01‑29	master vs Stockfish 14 _{Bench: 4637392 Do stats updates after LMR for captures [differences] 159}	Elo: 32.07 ±1.0 _{Ptnml: 10, 1009, 22681, 6049, 251 nElo: 93.05 ±2.5 PairsRatio: 6.18 [raw statistics]}	Elo: 22.31 ±1.0 _{Ptnml: 3, 496, 16495, 2945, 61 nElo: 76.78 ±3.0 PairsRatio: 6.02 [raw statistics]}
2022‑02‑10	master vs Stockfish 14 _{Bench: 4919707 Update architecture to "SFNNv4" [differences] 166}	Elo: 34.88 ±1.0 _{Ptnml: 13, 884, 22430, 6432, 241 nElo: 100.85 ±2.5 PairsRatio: 7.44 [raw statistics]}	Elo: 24.37 ±1.0 _{Ptnml: 2, 416, 16441, 3061, 80 nElo: 83.29 ±2.9 PairsRatio: 7.51 [raw statistics]}
2022‑02‑17	master vs Stockfish 14 _{Bench: 6318903 Tune search at very long time control [differences] 168}	Elo: 33.07 ±1.0 _{Ptnml: 17, 984, 22522, 6243, 234 nElo: 95.49 ±2.5 PairsRatio: 6.47 [raw statistics]}	Elo: 23.83 ±1.0 _{Ptnml: 4, 410, 16496, 3023, 67 nElo: 82.31 ±2.9 PairsRatio: 7.46 [raw statistics]}
2022‑03‑19	master vs Stockfish 14 _{Bench: 7044203 Remove ttPv tree shrinking [differences] 180}	Elo: 35.01 ±1.0 _{Ptnml: 11, 801, 22566, 6395, 227 nElo: 102.62 ±2.5 PairsRatio: 8.16 [raw statistics]}
2022‑04‑17	master vs Stockfish 14 _{Bench: 8129754 Decrease LMR at PV nodes with low depth [differences] 189}	Elo: 36.69 ±1.0 _{Ptnml: 5, 711, 22489, 6557, 238 nElo: 107.69 ±2.4 PairsRatio: 9.49 [raw statistics]}	Elo: 26.09 ±1.0 _{Ptnml: 1, 341, 16379, 3217, 62 nElo: 89.84 ±2.8 PairsRatio: 9.59 [raw statistics]}	Elo: 91.22 ±1.3 _{Ptnml: 17, 1335, 12388, 15750, 510 nElo: 205.62 ±3.6 PairsRatio: 12.03 [raw statistics]}
2022‑04‑18	Stockfish 15 _{Bench: 8129754 [differences] 190}

Stockfish 16 Development (2022-04-18 - 2023-06-29)

`Date`	`Version`	`1 Thread`	`8 Threads`	`1 Thread (UHO)`
2022‑05‑14	master vs Stockfish 15 _{Bench: 6481017 SE depth scaling using the previous depth [differences] 9}	Elo: 4.54 ±0.8 _{Ptnml: 18, 1850, 25507, 2580, 45 nElo: 16.29 ±2.8 PairsRatio: 1.41 [raw statistics]}	Elo: 3.12 ±0.8 _{Ptnml: 5, 803, 18029, 1154, 9 nElo: 13.92 ±3.4 PairsRatio: 1.44 [raw statistics]}
2022‑06‑16	master vs Stockfish 15 _{Bench: 5845802 Simplify away condition in ttSave in probCut [differences] 25}	Elo: 5.72 ±0.8 _{Ptnml: 31, 1838, 25288, 2799, 44 nElo: 19.99 ±2.8 PairsRatio: 1.52 [raw statistics]}
2022‑07‑13	master vs Stockfish 15 _{Bench: 5905619 Update default net to nn-ad9b42354671.nnue [differences] 34}	Elo: 5.70 ±0.8 _{Ptnml: 42, 1867, 25207, 2832, 52 nElo: 19.67 ±2.8 PairsRatio: 1.51 [raw statistics]}	Elo: 4.86 ±0.8 _{Ptnml: 3, 734, 17975, 1276, 12 nElo: 21.46 ±3.3 PairsRatio: 1.75 [raw statistics]}
2022‑08‑12	master vs Stockfish 15 _{Bench: 5868987 Remove an unneeded randomization of evals [differences] 43}	Elo: 7.18 ±0.8 _{Ptnml: 48, 1784, 25112, 2993, 63 nElo: 24.44 ±2.8 PairsRatio: 1.67 [raw statistics]}	Elo: 4.60 ±0.8 _{Ptnml: 5, 737, 17987, 1265, 6 nElo: 20.43 ±3.4 PairsRatio: 1.71 [raw statistics]}	Elo: 14.61 ±1.3 _{Ptnml: 149, 5043, 17073, 7608, 127 nElo: 30.73 ±2.8 PairsRatio: 1.49 [raw statistics]}
2022‑09‑07	master vs Stockfish 15 _{Bench: 5609606 VLTC tuning [differences] 52}	Elo: 6.87 ±0.8 _{Ptnml: 40, 1796, 25154, 2958, 52 nElo: 23.61 ±2.8 PairsRatio: 1.64 [raw statistics]}	Elo: 5.45 ±0.8 _{Ptnml: 3, 732, 17913, 1339, 13 nElo: 23.68 ±3.3 PairsRatio: 1.84 [raw statistics]}
2022‑10‑05	master vs Stockfish 15 _{Bench: 4114228 Revert "Mix alpha and statScore for reduction" [differences] 66}	Elo: 6.86 ±0.8 _{Ptnml: 21, 1580, 25632, 2727, 40 nElo: 25.04 ±2.7 PairsRatio: 1.73 [raw statistics]}	Elo: 5.98 ±0.8 _{Ptnml: 6, 643, 18015, 1329, 7 nElo: 26.72 ±3.3 PairsRatio: 2.06 [raw statistics]}
2022‑10‑30	master vs Stockfish 15 _{Bench: 4271738 Adjust reduction less at medium depths [differences] 81}	Elo: 8.52 ±0.8 _{Ptnml: 23, 1469, 25573, 2884, 51 nElo: 30.84 ±2.7 PairsRatio: 1.97 [raw statistics]}	Elo: 5.91 ±0.7 _{Ptnml: 6, 589, 18129, 1271, 5 nElo: 27.24 ±3.3 PairsRatio: 2.14 [raw statistics]}	Elo: 17.17 ±1.8 _{Ptnml: 38, 2430, 8572, 3933, 27 nElo: 36.91 ±4.0 PairsRatio: 1.60 [raw statistics]}
2022‑12‑02	master vs Stockfish 15 _{Bench: 3467381 Fix bestThread selection [differences] 97}	Elo: 7.46 ±0.7 _{Ptnml: 21, 1389, 25902, 2657, 31 nElo: 28.19 ±2.7 PairsRatio: 1.91 [raw statistics]}	Elo: 5.97 ±0.7 _{Ptnml: 3, 573, 18164, 1254, 6 nElo: 27.83 ±3.3 PairsRatio: 2.19 [raw statistics]}	Elo: 17.04 ±1.3 _{Ptnml: 73, 4844, 17208, 7820, 55 nElo: 36.73 ±2.8 PairsRatio: 1.60 [raw statistics]}
2022‑12‑04	Stockfish 15.1 _{Bench: 3467381 [differences] 98}
2022‑12‑19	master vs Stockfish 15 _{Bench: 3727508 Sometimes do a reduced search if LMR is skipped [differences] 119}	Elo: 8.55 ±0.8 _{Ptnml: 16, 1420, 25675, 2850, 39 nElo: 31.50 ±2.7 PairsRatio: 2.01 [raw statistics]}
2023‑01‑01	master vs Stockfish 15 _{Bench: 4015511 Update default net to nn-60fa44e376d9.nnue [differences] 126}	Elo: 10.00 ±0.8 _{Ptnml: 15, 1301, 25667, 2976, 41 nElo: 36.92 ±2.7 PairsRatio: 2.29 [raw statistics]}	Elo: 7.10 ±0.7 _{Ptnml: 6, 529, 18118, 1336, 11 nElo: 32.56 ±3.2 PairsRatio: 2.52 [raw statistics]}	Elo: 23.55 ±1.3 _{Ptnml: 59, 4354, 17132, 8377, 78 nElo: 51.05 ±2.8 PairsRatio: 1.92 [raw statistics]}
2023‑01‑23	master vs Stockfish 15 _{Bench: 3941848 Update default net to nn-bc24c101ada0.nnue [differences] 143}	Elo: 11.37 ±0.7 _{Ptnml: 9, 1127, 25786, 3048, 30 nElo: 42.95 ±2.7 PairsRatio: 2.71 [raw statistics]}	Elo: 9.09 ±0.8 _{Ptnml: 2, 484, 17984, 1526, 4 nElo: 40.84 ±3.2 PairsRatio: 3.15 [raw statistics]}	Elo: 29.49 ±1.3 _{Ptnml: 43, 3893, 17099, 8870, 95 nElo: 64.58 ±2.9 PairsRatio: 2.28 [raw statistics]}
2023‑02‑09	master vs Stockfish 15 _{Bench: 3841998 Update default net to nn-1337b1adec5b.nnue [differences] 162}	Elo: 12.76 ±0.8 _{Ptnml: 9, 1089, 25635, 3224, 43 nElo: 47.33 ±2.6 PairsRatio: 2.98 [raw statistics]}	Elo: 8.49 ±0.8 _{Ptnml: 2, 502, 18018, 1473, 5 nElo: 38.38 ±3.2 PairsRatio: 2.93 [raw statistics]}	Elo: 32.71 ±1.3 _{Ptnml: 44, 3760, 16821, 9269, 106 nElo: 71.26 ±2.9 PairsRatio: 2.46 [raw statistics]}
2023‑02‑18	master vs Stockfish 15 _{Bench: 4283297 Remove one reduction call [differences] 168}	Elo: 12.58 ±0.8 _{Ptnml: 11, 1127, 25591, 3221, 50 nElo: 46.26 ±2.6 PairsRatio: 2.87 [raw statistics]}		Elo: 31.91 ±1.3 _{Ptnml: 47, 3828, 16804, 9225, 96 nElo: 69.38 ±2.9 PairsRatio: 2.41 [raw statistics]}
2023‑02‑24	master vs Stockfish 15 _{Bench: 4705194 Search tuning at very long time control [differences] 174}	Elo: 11.69 ±0.7 _{Ptnml: 10, 1151, 25692, 3105, 42 nElo: 43.51 ±2.6 PairsRatio: 2.71 [raw statistics]}	Elo: 9.37 ±0.8 _{Ptnml: 1, 455, 18013, 1526, 5 nElo: 42.48 ±3.1 PairsRatio: 3.36 [raw statistics]}	Elo: 32.42 ±1.3 _{Ptnml: 44, 3804, 16761, 9307, 84 nElo: 70.59 ±2.9 PairsRatio: 2.44 [raw statistics]}
2023‑03‑19	master vs Stockfish 15 _{Bench: 4980082 Remove 'si' StateInfo variable/parameter. [differences] 196}	Elo: 13.36 ±0.8 _{Ptnml: 9, 1098, 25532, 3300, 61 nElo: 48.75 ±2.6 PairsRatio: 3.04 [raw statistics]}	Elo: 10.10 ±0.8 _{Ptnml: 0, 460, 17934, 1589, 17 nElo: 44.63 ±3.1 PairsRatio: 3.49 [raw statistics]}	Elo: 35.27 ±1.3 _{Ptnml: 48, 3610, 16657, 9594, 91 nElo: 76.91 ±2.9 PairsRatio: 2.65 [raw statistics]}
2023‑04‑01	master vs Stockfish 15 _{Bench: 4380438 Decrease Depth more for positions not in TT. [differences] 211}	Elo: 14.42 ±0.8 _{Ptnml: 7, 1031, 25480, 3431, 51 nElo: 52.68 ±2.6 PairsRatio: 3.35 [raw statistics]}	Elo: 9.90 ±0.8 _{Ptnml: 2, 450, 17964, 1575, 9 nElo: 44.20 ±3.1 PairsRatio: 3.50 [raw statistics]}	Elo: 37.37 ±1.3 _{Ptnml: 48, 3485, 16555, 9815, 97 nElo: 81.54 ±2.9 PairsRatio: 2.81 [raw statistics]}
2023‑04‑22	master vs Stockfish 15 _{Bench: 3548023 Less reduction for tt move. [differences] 235}	Elo: 14.60 ±0.8 _{Ptnml: 9, 967, 25569, 3405, 50 nElo: 53.91 ±2.6 PairsRatio: 3.54 [raw statistics]}	Elo: 11.32 ±0.8 _{Ptnml: 0, 386, 17939, 1661, 14 nElo: 50.39 ±3.0 PairsRatio: 4.34 [raw statistics]}	Elo: 38.07 ±1.3 _{Ptnml: 27, 3392, 16687, 9793, 101 nElo: 83.87 ±2.9 PairsRatio: 2.89 [raw statistics]}
2023‑05‑07	master vs Stockfish 15 _{Bench: 3808503 Refine deeper post-lmr searches [differences] 244}	Elo: 14.36 ±0.8 _{Ptnml: 11, 1004, 25521, 3423, 41 nElo: 52.83 ±2.6 PairsRatio: 3.41 [raw statistics]}	Elo: 10.63 ±0.7 _{Ptnml: 0, 379, 18029, 1581, 11 nElo: 48.41 ±3.0 PairsRatio: 4.20 [raw statistics]}	Elo: 39.62 ±1.3 _{Ptnml: 34, 3309, 16568, 9988, 101 nElo: 87.17 ±2.9 PairsRatio: 3.02 [raw statistics]}
2023‑06‑04	master vs Stockfish 15 _{Bench: 2551691 Move internal iterative reduction before probcut [differences] 265}	Elo: 15.01 ±0.8 _{Ptnml: 9, 1037, 25355, 3552, 47 nElo: 54.25 ±2.6 PairsRatio: 3.44 [raw statistics]}	Elo: 11.87 ±0.8 _{Ptnml: 3, 362, 17908, 1720, 7 nElo: 52.68 ±3.0 PairsRatio: 4.73 [raw statistics]}	Elo: 38.10 ±1.3 _{Ptnml: 48, 3387, 16634, 9826, 105 nElo: 83.49 ±2.9 PairsRatio: 2.89 [raw statistics]}
2023‑06‑12	master vs Stockfish 15 _{Bench: 2370027 Use block sparse input for the first layer. [differences] 274}	Elo: 17.57 ±0.8 _{Ptnml: 10, 881, 25223, 3840, 46 nElo: 63.12 ±2.5 PairsRatio: 4.36 [raw statistics]}	Elo: 13.95 ±0.8 _{Ptnml: 1, 290, 17828, 1865, 16 nElo: 60.93 ±2.8 PairsRatio: 6.46 [raw statistics]}	Elo: 44.18 ±1.3 _{Ptnml: 45, 3031, 16345, 10449, 130 nElo: 97.20 ±3.0 PairsRatio: 3.44 [raw statistics]}
2023‑06‑22	master vs Stockfish 15 _{Bench: 2593605 Update default net to nn-5af11540bbfe.nnue [differences] 289}	Elo: 18.30 ±0.8 _{Ptnml: 3, 812, 25265, 3864, 56 nElo: 66.19 ±2.5 PairsRatio: 4.81 [raw statistics]}	Elo: 14.33 ±0.8 _{Ptnml: 3, 297, 17767, 1914, 19 nElo: 61.59 ±2.9 PairsRatio: 6.44 [raw statistics]}	Elo: 47.03 ±1.3 _{Ptnml: 26, 2938, 16102, 10805, 129 nElo: 103.71 ±3.0 PairsRatio: 3.69 [raw statistics]}
2023‑06‑29	Stockfish 16 _{Bench: 2593605 [differences] 290}

Stockfish 17 Development (2023-06-29 - 2024-09-06)

`Date`	`Version`	`1 Thread`	`8 Threads`
2023‑07‑19	master vs Stockfish 16 _{Bench: 1727577 Do more futility pruning for cutNodes that are not in TT [differences] 41}	Elo: 0.10 ±1.4 _{Ptnml: 96, 6835, 16121, 6851, 97 nElo: 0.21 ±2.8 PairsRatio: 1.00 [raw statistics]}	Elo: 2.10 ±1.3 _{Ptnml: 30, 5872, 17820, 6261, 17 nElo: 4.64 ±2.8 PairsRatio: 1.06 [raw statistics]}
2023‑08‑13	master vs Stockfish 16 _{Bench: 1447866 Simplify material difference in evaluate [differences] 68}	Elo: 0.58 ±1.4 _{Ptnml: 120, 6787, 16066, 6927, 100 nElo: 1.17 ±2.8 PairsRatio: 1.02 [raw statistics]}	Elo: 2.08 ±1.2 _{Ptnml: 15, 5797, 18021, 6147, 20 nElo: 4.65 ±2.8 PairsRatio: 1.06 [raw statistics]}
2023‑09‑11	master vs Stockfish 16 _{Bench: 1603079 Cleanup code after dropping ICC support in favor of ICX [differences] 93}	Elo: 7.66 ±1.4 _{Ptnml: 86, 6160, 16212, 7429, 113 nElo: 15.68 ±2.8 PairsRatio: 1.21 [raw statistics]}	Elo: 5.65 ±1.2 _{Ptnml: 16, 5524, 17944, 6500, 16 nElo: 12.57 ±2.8 PairsRatio: 1.18 [raw statistics]}
2023‑09‑22	master vs Stockfish 16 _{Bench: 1246812 Update NNUE architecture to SFNNv8: L1-2560 nn-ac1dbea57aa3.nnue [differences] 103}	Elo: 3.33 ±1.4 _{Ptnml: 106, 6534, 16134, 7131, 95 nElo: 6.78 ±2.8 PairsRatio: 1.09 [raw statistics]}	Elo: 6.61 ±1.3 _{Ptnml: 21, 5553, 17713, 6689, 24 nElo: 14.56 ±2.8 PairsRatio: 1.20 [raw statistics]}
2023‑10‑08	master vs Stockfish 16 _{Bench: 1246560 Skip futility pruning if ttMove has bad history [differences] 119}	Elo: 9.68 ±1.4 _{Ptnml: 100, 6094, 15972, 7702, 132 nElo: 19.61 ±2.8 PairsRatio: 1.26 [raw statistics]}	Elo: 10.30 ±1.3 _{Ptnml: 13, 5168, 17868, 6930, 21 nElo: 22.90 ±2.8 PairsRatio: 1.34 [raw statistics]}
2023‑10‑23	master vs Stockfish 16 _{Bench: 1241996 Follow up Makefile changes for clang-format [differences] 136}	Elo: 10.47 ±1.4 _{Ptnml: 94, 6071, 15901, 7801, 133 nElo: 21.17 ±2.8 PairsRatio: 1.29 [raw statistics]}	Elo: 9.16 ±1.3 _{Ptnml: 19, 5311, 17763, 6884, 23 nElo: 20.24 ± 2.8 ParsRatio: 1.30 [raw statistics]}
2023‑11‑03	master vs Stockfish 16 _{Bench: 1330590 Update pawn history based on static eval difference [differences] 150}	Elo: 10.57 ±1.4 _{Ptnml: 112, 6018, 15922, 7829, 119 nElo: 21.38 ±2.8 PairsRatio: 1.30 [raw statistics]}	Elo: 9.16 ±1.3 _{Ptnml: 27, 5330, 17701, 6919, 23 nElo: 20.17 ±2.8 PairsRatio: 1.30 [raw statistics]}
2023‑12‑02	master vs Stockfish 16 _{Bench: 1403703 Tweak return value in futility pruning [differences] 172}	Elo: 12.59 ±1.4 _{Ptnml: 93, 5810, 16029, 7966, 102 nElo: 25.70 ±2.8 PairsRatio: 1.37 [raw statistics]}	Elo: 10.08 ±1.3 _{Ptnml: 18, 5168, 17893, 6897, 24 nElo: 22.42 ±2.8 PairsRatio: 1.33 [raw statistics]}
2023‑12‑31	master vs Stockfish 16 _{Bench: 1392883 Tweak static eval history update [differences] 202}	Elo: 19.19 ±1.4 _{Ptnml: 74, 5393, 15884, 8446, 203 nElo: 38.89 ±2.8 PairsRatio: 1.58 [raw statistics]}	Elo: 16.82 ±1.3 _{Ptnml: 13, 4672, 17747, 7535, 33 nElo: 37.42 ±2.8 PairsRatio: 1.62 [raw statistics]}
2024‑01‑07	master vs Stockfish 16 _{Bench: 1438336 Prefix abs with std:: [differences] 219}	Elo: 25.53 ±1.4 _{Ptnml: 58, 4917, 15789, 9038, 198 nElo: 52.14 ±2.8 PairsRatio: 1.86 [raw statistics]}	Elo: 18.88 ±1.3 _{Ptnml: 12, 4602, 17534, 7820, 32 nElo: 41.76 ±2.8 PairsRatio: 1.70 [raw statistics]}
2024‑01‑21	master vs Stockfish 16 _{Bench: 1235377 VLTC search tune [differences] 242}	Elo: 26.49 ±1.4 _{Ptnml: 64, 4791, 15823, 9159, 163 nElo: 54.42 ±2.8 PairsRatio: 1.92 [raw statistics]}	Elo: 22.91 ±1.2 _{Ptnml: 12, 4114, 17807, 8046, 21 nElo: 51.64 ±2.8 PairsRatio: 1.96 [raw statistics]}
2024‑02‑11	master vs Stockfish 16 _{Bench: 1027182 Format code using clang-format [differences] 269}	Elo: 22.81 ±1.4 _{Ptnml: 81, 5104, 15792, 8846, 177 nElo: 46.39 ±2.8 PairsRatio: 1.74 [raw statistics]}	Elo: 22.13 ±1.3 _{Ptnml: 22, 4312, 17524, 8112, 30 nElo: 49.11 ±2.8 PairsRatio: 1.88 [raw statistics]}
2024‑02‑17	master vs Stockfish 16 _{Bench: 1303971 Simplify PV node reduction [differences] 276}	Elo: 27.04 ±1.4 _{Ptnml: 65, 4832, 15656, 9272, 175 nElo: 55.20 ±2.9 PairsRatio: 1.93 [raw statistics]}	Elo: 27.03 ±1.2 _{Ptnml: 16, 3891, 17544, 8517, 32 nElo: 60.62 ±2.9 PairsRatio: 2.19 [raw statistics]}
2024‑02‑24	Stockfish 16.1 _{Bench: 1303971 [differences] 280}
2024‑03‑12	master vs Stockfish 16 _{Bench: 1715522 Search + Eval + Movepick Tune [differences] 302}	Elo: 27.13 ±1.4 _{Ptnml: 79, 4801, 15674, 9257, 189 nElo: 55.27 ±2.9 PairsRatio: 1.94 [raw statistics]}	Elo: 29.99 ±1.2 _{Ptnml: 15, 3656, 17515, 8775, 39 nElo: 67.59 ±2.9 PairsRatio: 2.40 [raw statistics]}
2024‑03‑29	master vs Stockfish 16 _{Bench: 1759189 Simplify NMP Condition [differences] 322}	Elo: 27.73 ±1.4 _{Ptnml: 80, 4736, 15703, 9287, 194 nElo: 56.57 ±2.9 PairsRatio: 1.97 [raw statistics]}	Elo: 30.03 ±1.2 _{Ptnml: 16, 3637, 17534, 8784, 29 nElo: 67.81 ±2.9 PairsRatio: 2.41 [raw statistics]}
2024‑04‑11	master vs Stockfish 16 _{Bench: 1479416 Simplify the depth-dependent part of the best value adjustment formula in main search [differences] 333}	Elo: 23.53 ±1.4 _{Ptnml: 75, 5095, 15696, 8965, 169 nElo: 47.82 ±2.8 PairsRatio: 1.77 [raw statistics]}	Elo: 35.27 ±1.2 _{Ptnml: 10, 3235, 17465, 9255, 35 nElo: 80.49 ±2.9 PairsRatio: 2.86 [raw statistics]}
2024‑04‑24	master vs Stockfish 16 _{Bench: 1836777 Implement accumulator refresh table [differences] 348}	Elo: 32.04 ±1.4 _{Ptnml: 51, 4471, 15578, 9709, 191 nElo: 65.84 ±2.9 PairsRatio: 2.19 [raw statistics]}	Elo: 37.86 ±1.2 _{Ptnml: 7, 3255, 17012, 9670, 56 nElo: 85.18 ±2.9 PairsRatio: 2.98 [raw statistics]}
2024‑05‑05	master vs Stockfish 16 _{Bench: 2180675 VVLTC search tune [differences] 369}	Elo: 28.90 ±1.4 _{Ptnml: 70, 4716, 15571, 9451, 192 nElo: 58.87 ±2.9 PairsRatio: 2.01 [raw statistics]}	Elo: 40.41 ±1.2 _{Ptnml: 6, 3047, 16994, 9899, 54 nElo: 91.59 ±2.9 PairsRatio: 3.26 [raw statistics]}
2024‑05‑13	master vs Stockfish 16 _{Bench: 1876282 Optimize update_accumulator_refresh_cache() [differences] 386}	Elo: 28.23 ±1.4 _{Ptnml: 94, 4694, 15651, 9376, 185 nElo: 57.50 ±2.9 PairsRatio: 2.00 [raw statistics]}	Elo: 39.08 ±1.2 _{Ptnml: 12, 3037, 17207, 9707, 37 nElo: 89.14 ±2.9 PairsRatio: 3.20 [raw statistics]}
2024‑05‑18	master vs Stockfish 16 _{Bench: 1198142 VVLTC search tune [differences] 405}	Elo: 26.54 ±1.4 _{Ptnml: 78, 4876, 15650, 9185, 211 nElo: 53.85 ±2.8 PairsRatio: 1.90 [raw statistics]}	Elo: 38.55 ±1.2 _{Ptnml: 11, 3150, 17089, 9698, 52 nElo: 87.18 ±2.9 PairsRatio: 3.08 [raw statistics]}
2024‑05‑28	master vs Stockfish 16 _{Bench: 1856147 Improve performance on NUMA systems [differences] 433}	Elo: 30.13 ±1.4 _{Ptnml: 65, 4557, 15687, 9504, 187 nElo: 61.85 ±2.9 PairsRatio: 2.10 [raw statistics]}	Elo: 39.34 ±1.2 _{Ptnml: 6, 3094, 17063, 9803, 34 nElo: 89.36 ±2.9 PairsRatio: 3.17 [raw statistics]}
2024‑06‑08	master vs Stockfish 16 _{Bench: 1174094 Make repeated bench runs identical [differences] 490}	Elo: 35.60 ±1.4 _{Ptnml: 70, 4218, 15445, 10049, 218 nElo: 73.01 ±2.9 PairsRatio: 2.39 [raw statistics]}	Elo: 39.31 ±1.2 _{Ptnml: 15, 3169, 16895, 9884, 37 nElo: 88.49 ±2.9 PairsRatio: 3.12 [raw statistics]}
2024‑07‑01	master vs Stockfish 16 _{Bench: 1227870 Probcut in check no matter if pv or capture [differences] 517}	Elo: 40.07 ±1.4 _{Ptnml: 83, 3933, 15243, 10493, 248 nElo: 82.11 ±2.9 PairsRatio: 2.67 [raw statistics]}	Elo: 40.34 ±1.2 _{Ptnml: 11, 3043, 16987, 9918, 41 nElo: 91.47 ±2.9 PairsRatio: 3.26 [raw statistics]}
2024‑07‑09	master vs Stockfish 16 _{Bench: 1300471 Move Loop Consistency in Probcut [differences] 548}	Elo: 41.51 ±1.4 _{Ptnml: 68, 3769, 15319, 10649, 195 nElo: 86.22 ±3.0 PairsRatio: 2.83 [raw statistics]}	Elo: 43.42 ±1.2 _{Ptnml: 15, 2811, 16912, 10224, 38 nElo: 99.12 ±3.0 PairsRatio: 3.63 [raw statistics]}
2024‑07‑23	master vs Stockfish 16 _{Bench: 1371485 Update default main net to nn-31337bea577c.nnue [differences] 578}	Elo: 42.30 ±1.4 _{Ptnml: 59, 3800, 15131, 10833, 177 nElo: 87.72 ±3.0 PairsRatio: 2.85 [raw statistics]}	Elo: 45.06 ±1.2 _{Ptnml: 14, 2685, 16907, 10337, 57 nElo: 103.20 ±3.0 PairsRatio: 3.85 [raw statistics]}
2024‑08‑20	master vs Stockfish 16 _{Bench: 1484730 Tweak late move extensions [differences] 595}	Elo: 44.12 ±1.4 _{Ptnml: 69, 3686, 15064, 10960, 221 nElo: 91.20 ±3.0 PairsRatio: 2.98 [raw statistics]}	Elo: 44.32 ±1.2 _{Ptnml: 16, 2814, 16741, 10400, 29 nElo: 100.85 ±3.0 PairsRatio: 3.69 [raw statistics]}
2024‑09‑03	master vs Stockfish 16 _{Bench: 1484730 Update Top CPU Contributors [differences] 601}	Elo: 46.04 ±1.3 _{Ptnml: 50, 3562, 15030, 11150, 208 nElo: 95.92 ±3.0 PairsRatio: 3.14 [raw statistics]}	Elo: 42.62 ±1.2 _{Ptnml: 15, 2882, 16912, 10147, 44 nElo: 96.95 ±3.0 PairsRatio: 3.52 [raw statistics]}
2024‑09‑06	Stockfish 17 _{Bench: 1484730 [differences] 602}

External Links

There are several pages on the web run by chess engine fans. Some collect progress of Stockfish over previous stable versions and development builds. Some compare Stockfish progress to other chess engines. Here is a collection of some useful links in that regard.

Progression / Regression Tests ​

Current Development ​

Version Comparison ​

Elo Progression ​

Normalized Elo Progression ​

Game Pair Ratio Progression ​

30 Day Average ​

Draw Percentage vs Elo ​

Historical Information ​

External Links ​