chessbench.orgRanks LLMs by their ability to plan, predict and adapt.
MadeByLupu@bylupu
MadeByLupu@bylupu

Live match⁠

MiMo V2.6 Flash vs GPT-6 Luna

Back to home

GPT-6 Luna (Medium) — Unranked

+1
20 moves0 rejected≥ $0.0000 API cost
Turn3.5s
Total1.0m
B
W+4.9
Blunder on g5a8b7c6d5e4f3g2h1

MiMo V2.6 Flash (Thinking) — 1395

−1
20 moves1 rejected$0.0458 API cost
Turn167.0s
Total52.9m
Live · White is thinking
Evaluation historyWhite ↑ · Black ↓ +4.9
Move 1 · e4 · +0.3Move 2 · e5 · +0.3Move 3 · Nf3 · +0.3Move 4 · Nc6 · +0.3Move 5 · Bc4 · +0.2Move 6 · Nf6 · +0.3Move 7 · Ng5 · +0.0Move 8 · d5 · +0.1Move 9 · exd5 · +0.1Move 10 · Nxd5 · +0.7Move 11 · Nxf7 · +1.1Move 12 · Kxf7 · +0.8Move 13 · Qf3+ · +1.1Move 14 · Ke6 · +1.1Move 15 · Nc3 · +1.1Move 16 · Qf6 · +3.3Move 17 · Qxf6+ · +1.8Move 18 · gxf6 · +1.8Move 19 · Nxd5 · +1.7Move 20 · Kd7 · +4.2Move 21 · O-O · +3.0Move 22 · Bg7 · +3.5Move 23 · Re1 · +1.8Move 24 · e4 · +5.2Move 25 · d3 · +4.8Move 26 · Ne5 · +5.0Move 27 · Bb5+ · +0.5Move 28 · c6 · +0.4Move 29 · Bxc6+ · -3.7Move 30 · bxc6 · -3.1Move 31 · Nc3 · -3.7Move 32 · Nf3+ · +2.2Move 33 · gxf3 · +2.3Move 34 · exf3 · +2.8Move 35 · Re3 · +2.9Move 36 · Bb7 · +4.5Move 37 · Rxf3 · +4.2Move 38 · Rad8 · +5.1Move 39 · Bg5 · +0.9Move 40 · fxg5 · +4.9
StartViewer-only Stockfish · 40/40 positions evaluated40 moves
View previous matches