| Version | Release Date | CCRL 40/15 | CCRL Blitz | ipman r9 list | Chess324 Top15 | SP-CC Top 15 |
|---|---|---|---|---|---|---|
| 2.0 | 2026-06-27 | 3615 (#4) | 3752 (#5) | 3575* | 3821 (#4) | 3795 (#6) |
| 1.9 | 2026-01-04 | 3587 (#10) | 3727 (#13) | 3537 (#12) | 3734 (#8) | 3680 (#14) |
| 1.8 | 2025-07-22 | 3564 (#20) | 3697 (#16) | 3517 | 3680 (#12) | |
| 1.7 | 2025-05-31 | 3528 | 3642 | 3448 | ||
| 1.6.1 | 2025-05-15 | 3500* | 3622 | |||
| 1.6 | 2025-04-27 | 3490 | 3600* | |||
| 1.5 | 2025-04-18 | 3450* | 3500 | |||
| 1.4.1 | 2025-04-05 | 3425 | 3450* | |||
| 1.3.1415 | 2025-03-14 | 3365 | 3401 | |||
| 1.3 | 2025-03-07 | 3201 | ||||
| 1.2 | 2025-02-21 | 3120 | ||||
| 1.1 | 2025-01-24 | 2432 | ||||
| 1.0 | 2025-01-20 | 2100* |
All ratings and rankings are recorded at the time when they first appeared on the list, and as such they be out of date.
Supports FRC, also known as Chess960
The search is a standard alpha-beta search with many enhancements.
The evaluation is done using a neural net trained on self play games from zero knowledge, as well as games played by Vine, the MCTS Chess engine that @aronpetko and I have been working on. The networks are trained using the excellent open source bullet neural network trainer. For specifics about the network please see src/nnue/arch.zig.
- Get the network with
git submodule update --init --depth 1 - Install zig (0.16.0)
zig build --release=fast --prefix <installation path>(for example--prefix ~/.localwill put pawnocchio in~/.local/bin/pawnocchio) The Makefile is only intended to be used for testing on Openbench.
- The code is licensed under the GPLv3 license. Full text can be found in LICENSE in the project root
- The assets are licensed under the CC-BY-ND 4.0 license. Full text can be found in assets/LICENSE
- Many strong open source chess engines, but above all Stormphrax has been a massive source of inspiration
- Pyrrhic by Andrew Grant for tablebase probing, under the MIT license.
- src/bounded_array.zig from the zig standard library under the MIT License with some minor modifications.
- Jackal by snekkers for inspiration for styling this readme