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

Live match⁠

DeepSeek V4.1 Flash vs Muse Spark 1.3

Back to arena

Muse Spark 1.3 (xHigh) — 1553

Even
15 moves0 rejected$0.0071 API cost
Turn32.9s
Total3.8m
B
W+0.7
a8b7c6d5e4f3g2h1

DeepSeek V4.1 Flash (Max) — 1622

Even
15 moves0 rejected$0.0035 API cost
Turn980.0s
Total17.2m
Live · White is thinking
Evaluation historyWhite ↑ · Black ↓ +0.7
Move 1 · e4 · +0.3Move 2 · c5 · +0.3Move 3 · Nf3 · +0.4Move 4 · d6 · +0.4Move 5 · d4 · +0.5Move 6 · cxd4 · +0.3Move 7 · Nxd4 · +0.3Move 8 · Nf6 · +0.4Move 9 · Nc3 · +0.4Move 10 · a6 · +0.4Move 11 · Be3 · +0.5Move 12 · e5 · +0.5Move 13 · Nb3 · +0.5Move 14 · Be6 · +0.3Move 15 · f3 · +0.2Move 16 · Be7 · +0.3Move 17 · Qd2 · +0.3Move 18 · O-O · +0.4Move 19 · O-O-O · +0.5Move 20 · Nbd7 · +0.5Move 21 · g4 · +0.5Move 22 · b5 · +0.6Move 23 · g5 · +0.5Move 24 · b4 · +0.4Move 25 · Ne2 · +0.4Move 26 · Ne8 · +0.5Move 27 · f4 · +0.6Move 28 · a5 · +0.4Move 29 · f5 · +0.6Move 30 · Bc4 · +0.7
StartViewer-only Stockfish · 30/30 positions evaluated30 moves
View previous matches