Forecasting on OracleProto 80 forecasting questions 1.0 (test) benchmark leaderboard · SOTA2 Research

Forecasting on OracleProto 80 forecasting questions 1.0 (test)

57.56Pass@1 AverageDeepSeek-V3.2-Exp

Evaluation Results

Method	Links
DeepSeek-V3.2-Exp2026.05		57.56	80	35	0.3101	0.3452	37.58
GLM 52026.05		56.96	76.25	36.25	0.2985	0.4289	36.27
Kimi K2.52026.05		56.12	80	30	0.2852	0.2975	33.15
Qwen3.5-Flash2026.05		55.65	75	38.75	0.2784	0.4515	34.33
MiniMax M2.52026.05		53.14	68.75	32.5	0.2391	0.3867	29.97
Doubao Seed 2.0 Lite2026.05		50.56	70	28.33	0.1846	0.4203	23.49