Share your thoughts, 1 month free Claude Pro on usSee more

Probabilistic Forecasting on Metaculus and Polymarket (test)

0.061Brier Score

Human Baseline

Updated 6d ago

Evaluation Results

Method	Links
Human Baseline 2026.05		0.061	92.3	95.8	0.055	-
BBC (binary+human) 2026.05		0.125	83.7	74.2	0.027	8.775
BBC (binary only) 2026.05		0.128	83.3	73.2	0.036	9.004
Platt Scaling 2026.05		0.129	82.7	72.3	0.034	-
Isotonic Regression 2026.05		0.129	83.2	72.4	0.038	-
BBC (binary+human) 2026.05		0.133	83.3	68.6	0.046	9.402
BBC (binary+human) 2026.05		0.135	82.9	67.9	0.045	9.526
BBC (binary only) 2026.05		0.135	83.2	68.4	0.044	11.085
Isotonic Regression 2026.05		0.137	82.3	66.2	0.04	-
Future-as-a-label-32B 2026.05		0.137	82.9	67.7	0.046	-
BBC (binary+human) 2026.05		0.137	82.8	67.3	0.05	9.73
Isotonic Regression 2026.05		0.138	82.2	65.4	0.043	-
BBC (binary only) 2026.05		0.138	81.6	67.1	0.054	11.564
BBC (binary only) 2026.05		0.138	82.4	66.2	0.044	11.55
Platt Scaling 2026.05		0.139	82.9	65.5	0.051	-
Isotonic Regression 2026.05		0.141	81.8	63.8	0.054	-
Platt Scaling 2026.05		0.142	82.7	66.1	0.079	-
Ensemble (n = 3) 2026.05		0.143	80	73.6	0.1	-
Ensemble (n = 10) 2026.05		0.143	81.3	70	0.097	-
Verbalized 2026.05		0.146	79.9	72.3	0.104	-
Ensemble (n = 10) 2026.05		0.151	78.2	66.9	0.099	-
Platt Scaling 2026.05		0.151	82.3	63.3	0.094	-
Verbalized 2026.05		0.157	77.7	65.5	0.119	-
OpenForecaster-8B 2026.05		0.157	79.4	66.3	0.084	-
Verbalized 2026.05		0.158	79.6	66.1	0.111	-
Ensemble (n = 10) 2026.05		0.169	75.5	66.1	0.148	-
Verbalized 2026.05		0.185	75	63.3	0.164	-
P(True) 2026.05		0.222	77.2	61.9	0.22	-
P(True) 2026.05		0.232	76.1	66.4	0.23	-
P(True) 2026.05		0.265	72.6	65.6	0.265	-