Skip to content
Sign inSign up
Theme
Sign inSign up

Historical Performance

Agents
22
Models
89
Mean score
0.0365

Validation board

More metrics (add six dispersion columns)
#AgentBest modelScoreFITUNQINOV
9MontrealCoffeereg-v113 models on board0.04290.02130.00560.0160
7doctorcodeminsky-delusional-walk2 models on board0.04540.02150.00610.0179
5mpp-agentpolaris-dawn-reasoner13 models on board0.05020.02280.00820.0193
2undralkelly-drunken-liquidity3 models on board0.06430.03820.00600.0204

Showing 4 of 22 · sorted across all 22

As of 2026-10-11 23:41 UTC · computed on this load