List your company
ResearchFormerly WizWand

Forecasting on Forecasting (test)

0.133Brier ScoreBBC (binary+human)
0.127880.162440.1970.23156May 26, 2026
Updated 5mo ago

Evaluation results

MethodLinks
BBC (binary+human)Input LLM=Qwen2.5-72B-Instruct2026.050.13382.968.30.0359.16
BBC (binary only)Input LLM=Qwen2.5-72B-Instruct2026.050.13582.5670.04211.247
BBC (binary+human)Input LLM=Qwen2.5-7B-Instruct2026.050.13583.167.60.0549.677
BBC (binary+human)Input LLM=Llama-3.1-8B-Instruct2026.050.13682.867.30.0589.815
Platt ScalingInput LLM=Qwen2.5-72B-Instruct2026.050.13882.565.50.049—
Isotonic RegressionInput LLM=Qwen2.5-72B-Instruct2026.050.13882.565.50.044—
BBC (binary only)Input LLM=Qwen2.5-7B-Instruct2026.050.1388366.80.06712.227
BBC (binary only)Input LLM=Llama-3.1-8B-Instruct2026.050.13881.966.90.05511.703
Isotonic RegressionInput LLM=Qwen2.5-7B-Instruct2026.050.1482.662.40.064—
Isotonic RegressionInput LLM=Llama-3.1-8B-Instruct2026.050.14382.363.70.06—
Platt ScalingInput LLM=Llama-3.1-8B-Instruct2026.050.14482.763.90.069—
Platt ScalingInput LLM=Qwen2.5-7B-Instruct2026.050.14582.962.10.085—
Ensemble (n = 10)Input LLM=Qwen2.5-7B-Instruct2026.050.15979.764.60.121—
Ensemble (n = 10)Input LLM=Qwen2.5-72B-Instruct2026.050.16576.667.60.138—
Ensemble (n = 10)Input LLM=Llama-3.1-8B-Instruct2026.050.16576.666.20.153—
P(True)Input LLM=Qwen2.5-7B-Instruct2026.050.16682.756.80.165—
VerbalizedInput LLM=Llama-3.1-8B-Instruct2026.050.16977.163.90.14—
VerbalizedInput LLM=Qwen2.5-7B-Instruct2026.050.1777.862.10.124—
VerbalizedInput LLM=Qwen2.5-72B-Instruct2026.050.17476.465.50.144—
P(True)Input LLM=Llama-3.1-8B-Instruct2026.050.21776.862.30.216—
P(True)Input LLM=Qwen2.5-72B-Instruct2026.050.26173.663.30.262—