Benchmark · ReasoningCompetitive

Chess Puzzles

Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.

Updated 2026-03-05
Models tested
24
Top score
58.6
GPT-5.4 Pro
Median
20.0
min 4.0
Top-5 spread
σ 7.4
wide open

Best score over time · one chart, every benchmark

CHESS PUZZLES23 MODELS · FRONTIER RUNNING MAX0255075100SCORE ↑Jan 25May 25Aug 25Nov 25Mar 26RELEASE DATE →benchgecko.ai/benchmark/chess-puzzles · frontier
Frontier on Chess Puzzles rose from 17.0 to 58.6 in 13 months · +41.6 points · latest leader GPT-5.4 Pro from OpenAI.
Pink dots = frontier records · 7 totalClick to open model page
Details
Category
Reasoning
Max score
100
Models
24
Updated
2026-03-05

Same category · related evaluations