Provider	Model	Total	Reasoning (4)	History (4)	Humanities (5)	Science (5)	Coding (5)	Creativity (4)	Opinion (4)	Math (5)	Philosophy (5)	Engineering (5)
OpenAI	o3-pro	1,266	1185	1143	1115	980	1104	1055	1125	1034	1135	1122
OpenAI	GPT-5-mini	1,212	1060	1047	1077	1172	1032	1109	1063	1103	1115	1131
OpenAI	GPT-5	1,161	1111	1102	1181	1092	1088	1197	1119	1029	1046	1142
OpenAI	GPT-OSS	1,160	1010	1082	1051	1052	1062	995	1086	1076	1073	1202
OpenAI	o3	1,150	1200	1151	1256	1113	953	1100	1240	1027	1057	1115
OpenAI	GPT-5-nano	1,087	1022	1072	1010	1012	1062	1016	1034	1079	1034	1086
DeepSeek	R1	1,058	991	1059	996	1090	873	1071	1098	1011	1079	992
DeepSeek	V3-1-thinking	1,031	1034	1053	1052	1021	986	964	982	978	1141	922
Qwen	Qwen-3-thinking	980	1051	894	1053	994	1037	938	1011	1112	962	962
MoonshotAI	kimi-k2	973	845	1008	1010	1048	944	963	919	929	1093	987
DeepSeek	V3-1	965	911	1009	1052	1000	871	960	1005	1011	1029	998
Anthropic	Claude-opus-4-1	947	1062	966	948	901	1191	963	933	1000	1010	895
xAI	Grok-4	897	946	982	912	896	1021	895	837	913	768	829
OpenAI	o4-mini	878	981	953	962	1025	946	1069	1086	1017	930	1038
Google	Gemini-2.5-flash	871	816	858	880	916	985	924	874	919	907	888
Google	Gemini-2.5-pro	855	919	871	806	900	1025	938	798	931	804	866
Anthropic	Claude-sonnet-4	791	959	891	858	850	959	935	950	879	891	908
Qwen	Qwen-3-coder	718	900	858	779	941	861	907	841	954	927	917