As usual, downloads will be freely available at stockfishchess.org/download.
The engine is now significantly stronger than just a few months ago, and wins four times more game pairs than it loses against the previous release version. Stockfish 14 is now at least 400 Elo ahead of Stockfish 7, a top engine in 2016. During the last five years, Stockfish has thus gained about 80 Elo per year.
Stockfish 14 evaluates positions more accurately than Stockfish 13 as a result of two major steps forward in defining and training the efficiently updatable neural network (NNUE) that provides the evaluation for positions.
First, the collaboration with the Leela Chess Zero team - announced previously - has come to fruition. The LCZero team has provided a collection of billions of positions evaluated by Leela that we have combined with billions of positions evaluated by Stockfish to train the NNUE net that powers Stockfish 14. The fact that we could use and combine these datasets freely was essential for the progress made and demonstrates the power of open source and open data.
Second, the architecture of the NNUE network was significantly updated: the new network is not only larger, but more importantly, it deals better with large material imbalances and can specialize for multiple phases of the game. A new project, kick-started by Gary Linscott and Tomasz Sobczyk, led to a GPU accelerated net trainer written in pytorch. This tool allows for training high-quality nets in a couple of hours.
Finally, this release features some search refinements, minor bug fixes and additional improvements. For example, Stockfish is now about 90 Elo stronger for chess960 (Fischer random chess) at short time control.
The Stockfish project builds on a thriving community of enthusiasts (thanks everybody!) that contribute their expertise, time, and resources to build a free and open-source chess engine that is robust, widely available, and very strong. We invite our chess fans to join the fishtest testing framework and programmers to contribute to the project on github.
PGN:
1. e4 e5 2. Nf3 Nc6 3. Bc4 Nf6 4. Ng5 d5 5. exd5 Nxd5 6. Nxf7 Kxf7 7. Qf3+ Ke6 8. Nc3 Nb4 9. O-O c6 10. d4 Qf6 11. Qe2 Ke7 12. dxe5 Qg6 13. Ne4 Bf5 14. f3 Kd7 15. a3 Na6 16. Bxa6 bxa6 17. Qxa6 Kc7 18. c4 Bxe4 19. fxe4 Bc5+ 20. Kh1 Ne7 21. Bf4 Rhf8 22. e6+ Rxf4 23. Rxf4 Qxe6 24. Raf1 Rc8 25. Qa5+ Bb6 26. Qc3 Kb8 27. Rf7 c5 28. Rxg7 Nc6 29. Rxh7 Qxe4 30. Rhf7 Nd4 31. b4 Rg8 32. Rf8+ Rxf8 33. Rxf8+ Kb7 34. Rf1 Qe6 35. Re1 Qd6 36. Qd2 Kc8 37. g4 cxb4 38. axb4 Qc6+ 39. Qg2 Qxc4 40. g5 Qxb4 41. Qe4 Qc5 42. g6 Nf5 43. Rf1 Nh6 44. g7 Kb8 45. Rf8+ Kc7 46. Rf7+ Nxf7 47. Qf4+ Nd6 48. g8=Q Qc6+ 49. Qg2 Qc3 50. h4 Bd4 51. Qe2 Kc6 52. Kg2 Qc5 53. h5 Kb6 54. Qe6 Qc2+ 55. Kh3 Bc5 56. h6 Qd1 57. Qg3 Qh1+ 58. Kg4 Qd1+ 59. Qf3 Qc2 60. Qfb3+ Qxb3 61. Qxb3+ Nb5 62. Kf3 Bd4 63. Ke4 Ba1 64. Kd3 Kc5 65. Qc2+ Kb6 66. Qf2+ Kb7 67. Qg2+ Kc7