Provider	Model	Total	History (4)	Humanities (5)	Opinion (4)	Creativity (4)	Coding (5)	Science (5)	Philosophy (5)	Math (5)	Reasoning (4)	Engineering (5)
Moonshot	Kimi-k2.5	1,181	1098	1124	1021	1076	1072	995	1063	1066	1082	1032
OpenAI	GPT-OSS	1,079	1041	967	1148	981	1041	992	1072	1058	1064	1216
Anthropic	Claude-Opus-4-5	1,102	964	987	1030	1002	997	1007	1129	1053	1013	1068
Google	Gemini-3-Flash	1,044	904	1067	973	910	1056	890	1012	1049	1049	1066
Qwen	Qwen-3-thinking	1,005	982	993	1055	883	994	1083	977	1033	1019	971
Google	Gemini-3-Pro	994	1016	1038	1002	1017	1016	1027	970	1030	998	1025
Z	GLM-4.7	894	972	991	912	934	1003	945	932	1023	968	984
OpenAI	GPT-5.2	1,148	1064	1017	1017	1139	1078	1168	1047	1013	1071	1013
DeepSeek	R1	1,013	1006	1028	1124	1030	891	1070	1048	995	966	846
xAI	Grok-4-1-fast	842	884	968	915	963	997	935	961	981	974	888
OpenAI	o4-mini	913	955	934	976	982	996	964	918	975	955	931
DeepSeek	V3-2-thinking	969	1008	1019	921	1074	964	935	1015	969	875	956
Z	GLM-5	871	1012	912	942	957	1009	871	933	932	988	953
Moonshot	Kimi-k2	865	980	904	926	1025	927	1044	920	920	947	976
OpenAI	GPT-5.1	1,081	1114	1050	1039	1025	962	1072	1002	903	1031	1075