Joel's Trading Benchmark: Jev 1.13 turns $1000 into $1031, below holding QQQ
A new benchmark gives each decision model $1000 for 90 real trading decisions, where perfect play would yield $3946; Jev 1.13 ends at $1031, under the $1038 from just holding QQQ.

I built a new benchmark (Joel's Trading Benchmark v1) for AI decision models, based on my test Trading bot (Nero DX) data collected in 2026 Each model gets $1000 and makes 90 real world trading decisions: which asset to hold right now, or none. Same data, real fees and zero future leakage Perfect decisions would have turned $1000 into $3946 Results: Microsoft-Decision-1: $1064 Jev 1.13: $1031 (Just holding QQQ with no decisions at all: $1038) The best model captured 2.2% of what was possible Which decision model should I test next?