TC: 1sec./move Book:Noomen 3moves
51300 games (Clean List update 11-11-2026) Total: 60000 games
=========================================================================
IPMAN CHESS – THE AI TRANSITION UPDATE
=========================================================================
The chess engine world is currently undergoing its biggest transition since the invention of bitboards and NNUE. Due to the rapid rise of AI-generated code and externally trained neural networks, some prominent testers have decided to close their top rating lists. Ipman Chess will not stop. We choose to look forward.
To address the strong feedback within the community and to keep the performance of traditional,human-written source code pure, I am temporarily introducing a separate category:
*** The AI & Experimental Transition List ***
Engines that rely heavily on AI code-generation, AI-coding assistants, or external neural network recipes (such as Coda, Gaia, Caipora, and Triumviratus) will be moved to this dedicated list.
Please note: this is a TEMPORARY separation. My 40 years of experience in engine testing has taught me that every technological leap—from Deep Blue to the first neural networks—initially faces heavy resistance, only to become the new standard later on.
As AI assistance becomes deeply integrated into all software development, these lists will inevitably merge back together.Until then, Ipman Chess will keep testing to witness and record history live: to see which engine—be it human, hybrid, or pure AI—will push the boundaries of computer chess further, and whether Stockfish can defend its legendary number one spot.
Maybe a change at the top will not happen soon, but as a neutral tester,I am excited to see what the future brings!
================================================================================
Classification Meta-Labels for the AI & Experimental Transition List:
[Agentic AI] = Code generated completely by an AI system (e.g., Claude Code).
[AI-Assisted] = Human-written code/base heavily modified or expanded by AI coding tools.
[NNUE-Ext-Recipe] = Human-written code, but neural network relies heavily on external AI training structures.
• Coda - Label: [Agentic AI]
Description:Developed entirely through human-AI collaboration; every single line of code was generated by Claude Code.
• Incipit - Label: [Agentic AI]
Description: Built from scratch using agent-driven AI coding throughout, focusing on independent knowledge generation.
• Caipora - Label: [Agentic AI]
Description: A project completely generated by Claude Code under human direction, utilizing a threat-aware NNUE structure.
• Triumviratus - Label: [AI-Assisted]
Description: Built upon a historical Stockfish source code base, but heavily modified, optimized, and expanded with AI development assistants.
• Zigqueen - Label: [AI-Assisted]
Description: Core implementation and features heavily driven by autonomous AI coding agents under human architectural review.
• GaiaChess - Label: [NNUE-Ext-Recipe]
Description: Code handcrafted by human authors, but moved to this list due to its heavy reliance on external AI training frameworks (Bullet/LC0 dataset).
IPMAN CHESS – THE AI TRANSITION UPDATE
=========================================================================
The chess engine world is currently undergoing its biggest transition since the invention of bitboards and NNUE. Due to the rapid rise of AI-generated code and externally trained neural networks, some prominent testers have decided to close their top rating lists. Ipman Chess will not stop. We choose to look forward.
To address the strong feedback within the community and to keep the performance of traditional,human-written source code pure, I am temporarily introducing a separate category:
*** The AI & Experimental Transition List ***
Engines that rely heavily on AI code-generation, AI-coding assistants, or external neural network recipes (such as Coda, Gaia, Caipora, and Triumviratus) will be moved to this dedicated list.
Please note: this is a TEMPORARY separation. My 40 years of experience in engine testing has taught me that every technological leap—from Deep Blue to the first neural networks—initially faces heavy resistance, only to become the new standard later on.
As AI assistance becomes deeply integrated into all software development, these lists will inevitably merge back together.Until then, Ipman Chess will keep testing to witness and record history live: to see which engine—be it human, hybrid, or pure AI—will push the boundaries of computer chess further, and whether Stockfish can defend its legendary number one spot.
Maybe a change at the top will not happen soon, but as a neutral tester,I am excited to see what the future brings!
================================================================================
Classification Meta-Labels for the AI & Experimental Transition List:
[Agentic AI] = Code generated completely by an AI system (e.g., Claude Code).
[AI-Assisted] = Human-written code/base heavily modified or expanded by AI coding tools.
[NNUE-Ext-Recipe] = Human-written code, but neural network relies heavily on external AI training structures.
• Coda - Label: [Agentic AI]
Description:Developed entirely through human-AI collaboration; every single line of code was generated by Claude Code.
• Incipit - Label: [Agentic AI]
Description: Built from scratch using agent-driven AI coding throughout, focusing on independent knowledge generation.
• Caipora - Label: [Agentic AI]
Description: A project completely generated by Claude Code under human direction, utilizing a threat-aware NNUE structure.
• Triumviratus - Label: [AI-Assisted]
Description: Built upon a historical Stockfish source code base, but heavily modified, optimized, and expanded with AI development assistants.
• Zigqueen - Label: [AI-Assisted]
Description: Core implementation and features heavily driven by autonomous AI coding agents under human architectural review.
• GaiaChess - Label: [NNUE-Ext-Recipe]
Description: Code handcrafted by human authors, but moved to this list due to its heavy reliance on external AI training frameworks (Bullet/LC0 dataset).
P.S. Please note that classifying these engines is an ongoing challenge. With so many new engines emerging, it is impossible for a tester to know if AI or AI-assist was used unless it is explicitly stated in the repository's GitHub or Readme. Furthermore, even established developers of traditional engines may choose to integrate AI assistance behind the scenes without public mention. Therefore, this list relies entirely on the transparency of the authors and the best available information.
Elostat & Ordo & BayesElo:
Rank Player EloStat ORDO BayesElo Games Score % Draw %
---------------------------------------------------------------------------------------------------- 1 Stockfish 20261109 avx512 3640.0 3643.1 3633.0 5,400 66.0 67.2
2 Triumviratus 8.1-dev avx512 3633.0 3635.6 3627.0 5,400 65.0 68.8
3 Triumviratus 8.0 avx512 3629.0 3631.3 3624.0 5,400 64.4 69.5
4 Gaia 4.4.3 avx512 3619.0 3620.9 3615.0 5,400 63.1 71.4
5 Coda 0.9.5 avx512 3605.0 3605.3 3604.0 5,400 61.0 71.9
6 Coda 0.9.4 AI avx2 3600.0 3600.0 3600.0 5,400 60.2 73.7
7 Gaia 4.4.1 avx512 3595.0 3594.7 3595.0 5,400 59.5 74.1
8 KestrelStrike 1.0 avx512 3573.0 3570.9 3577.0 5,400 56.2 75.6
9 Incipit 0.6.0 avx512 3556.0 3553.0 3563.0 5,400 53.7 73.8
10 Anna 1.2 avx2 3550.0 3546.1 3558.0 5,400 52.8 74.2
11 Ravager 3.0 avx512 3548.0 3543.9 3556.0 5,400 52.5 73.6
12 Zigqueen 6.5.0 avx512 3517.0 3510.8 3531.0 5,400 47.8 71.6
13 Incipit 0.5.0 avx512 3515.0 3508.7 3528.0 5,400 47.5 69.4
14 Heimdall 1.5.2 avx512 3487.0 3478.6 3505.0 5,400 43.4 68.3
15 FunComp 3.1 avx2 3461.0 3449.7 3481.0 5,400 39.4 63.6
16 FunComp 3.0 avx2 3440.0 3427.4 3463.0 5,400 36.5 60.4
17 Narc 5.1 avx512 3376.0 3359.7 3407.0 5,400 28.1 51.3
18 Narc 5.0 avx512 3364.0 3346.9 3396.0 5,400 26.6 49.3
19 Caipora 3.8 avx512 3362.0 3344.6 3395.0 5,400 26.3 48.5
Best version only:
Rank Player EloStat ORDO BayesElo Games Score % Draw %
---------------------------------------------------------------------------------------------------- 1 Stockfish 20261109 avx512 3640.0 3643.1 3633.0 5,400 66.0 67.2
2 Triumviratus 8.1-dev avx512 3633.0 3635.6 3627.0 5,400 65.0 68.8
3 Gaia 4.4.3 avx512 3619.0 3620.9 3615.0 5,400 63.1 71.4
4 Coda 0.9.5 avx512 3605.0 3605.3 3604.0 5,400 61.0 71.9
5 KestrelStrike 1.0 avx512 3573.0 3570.9 3577.0 5,400 56.2 75.6
6 Incipit 0.6.0 avx512 3556.0 3553.0 3563.0 5,400 53.7 73.8
7 Anna 1.2 avx2 3550.0 3546.1 3558.0 5,400 52.8 74.2
8 Ravager 3.0 avx512 3548.0 3543.9 3556.0 5,400 52.5 73.6
9 Zigqueen 6.5.0 avx512 3517.0 3510.8 3531.0 5,400 47.8 71.6
10 Heimdall 1.5.2 avx512 3487.0 3478.6 3505.0 5,400 43.4 68.3
11 FunComp 3.1 avx2 3461.0 3449.7 3481.0 5,400 39.4 63.6
12 Narc 5.1 avx512 3376.0 3359.7 3407.0 5,400 28.1 51.3
13 Caipora 3.8 avx512 3362.0 3344.6 3395.0 5,400 26.3 48.5
More Stats:
Rank Player Points Wins Draws Losses Opp Avg Gap
--------------------------------------------------------------------------------------------------- 1 Stockfish 20261109 avx512 3562.5 1,747 3,631 22 3523.9 7.0
2 Triumviratus 8.1-dev avx512 3509.5 1,652 3,715 33 3524.3 4.0
3 Triumviratus 8.0 avx512 3479.0 1,603 3,752 45 3524.5 10.0
4 Gaia 4.4.3 avx512 3405.0 1,477 3,856 67 3525.1 14.0
5 Coda 0.9.5 avx512 3292.0 1,350 3,884 166 3525.8 5.0
6 Coda 0.9.4 AI avx2 3253.5 1,263 3,981 156 3526.1 5.0
7 Gaia 4.4.1 avx512 3214.5 1,213 4,003 184 3526.4 22.0
8 KestrelStrike 1.0 avx512 3037.5 996 4,083 321 3527.6 17.0
9 Incipit 0.6.0 avx512 2902.0 910 3,984 506 3528.6 6.0
10 Anna 1.2 avx2 2850.5 848 4,005 547 3528.9 2.0
11 Ravager 3.0 avx512 2833.5 847 3,973 580 3529.0 31.0
12 Zigqueen 6.5.0 avx512 2582.5 648 3,869 883 3530.7 2.0
13 Incipit 0.5.0 avx512 2567.0 693 3,748 959 3530.8 28.0
14 Heimdall 1.5.2 avx512 2341.0 498 3,686 1,216 3532.4 26.0
15 FunComp 3.1 avx2 2128.5 410 3,437 1,553 3533.8 21.0
16 FunComp 3.0 avx2 1968.5 337 3,263 1,800 3535.0 64.0
17 Narc 5.1 avx512 1515.0 129 2,772 2,499 3538.6 12.0
18 Narc 5.0 avx512 1436.0 105 2,662 2,633 3539.2 2.0
19 Caipora 3.8 avx512 1422.0 113 2,618 2,669 3539.3
Generated by: Chess Rating Studio Pro III - Revision 1.27
Gauge: 100/100 (A+) - Strong list.
@Copyright Mark Young