{ "eval_date": "2026-07-05", "framework": "OpenCompass v1.2.0", "datasets": [ "abstract_algebra", "anatomy", "astronomy", "business_ethics", "clinical_knowledge", "college_biology", "college_chemistry", "college_computer_science", "college_mathematics", "college_medicine", "college_physics", "computer_security", "conceptual_physics", "econometrics", "electrical_engineering", "elementary_mathematics", "formal_logic", "global_facts", "high_school_biology", "high_school_chemistry", "high_school_computer_science", "high_school_european_history", "high_school_geography", "high_school_government_and_politics", "high_school_macroeconomics", "high_school_mathematics", "high_school_microeconomics", "high_school_physics", "high_school_psychology", "high_school_statistics", "high_school_us_history", "high_school_world_history", "human_aging", "human_sexuality", "international_law", "jurisprudence", "logical_fallacies", "machine_learning", "management", "marketing", "medical_genetics", "miscellaneous", "moral_disputes", "moral_scenarios", "nutrition", "philosophy", "prehistory", "professional_accounting", "professional_law", "professional_medicine", "professional_psychology", "public_relations", "security_studies", "sociology", "us_foreign_policy", "virology", "world_religions" ], "models": [ { "name": "deepseek-v4-pro", "total_questions": 14042, "total_correct": 12750, "overall_accuracy": 90.79903147699758, "datasets": { "abstract_algebra": { "accuracy": 94.0, "correct": 94, "total": 100 }, "anatomy": { "accuracy": 93.33, "correct": 126, "total": 135 }, "astronomy": { "accuracy": 96.05, "correct": 146, "total": 152 }, "business_ethics": { "accuracy": 86.0, "correct": 86, "total": 100 }, "clinical_knowledge": { "accuracy": 93.96, "correct": 249, "total": 265 }, "college_biology": { "accuracy": 97.22, "correct": 140, "total": 144 }, "college_chemistry": { "accuracy": 75.0, "correct": 75, "total": 100 }, "college_computer_science": { "accuracy": 92.0, "correct": 92, "total": 100 }, "college_mathematics": { "accuracy": 93.0, "correct": 93, "total": 100 }, "college_medicine": { "accuracy": 89.02, "correct": 154, "total": 173 }, "college_physics": { "accuracy": 100.0, "correct": 102, "total": 102 }, "computer_security": { "accuracy": 86.0, "correct": 86, "total": 100 }, "conceptual_physics": { "accuracy": 96.17, "correct": 226, "total": 235 }, "econometrics": { "accuracy": 85.09, "correct": 97, "total": 114 }, "electrical_engineering": { "accuracy": 91.03, "correct": 132, "total": 145 }, "elementary_mathematics": { "accuracy": 98.41, "correct": 372, "total": 378 }, "formal_logic": { "accuracy": 97.62, "correct": 123, "total": 126 }, "global_facts": { "accuracy": 72.0, "correct": 72, "total": 100 }, "high_school_biology": { "accuracy": 95.16, "correct": 295, "total": 310 }, "high_school_chemistry": { "accuracy": 94.58, "correct": 192, "total": 203 }, "high_school_computer_science": { "accuracy": 98.0, "correct": 98, "total": 100 }, "high_school_european_history": { "accuracy": 89.09, "correct": 147, "total": 165 }, "high_school_geography": { "accuracy": 95.45, "correct": 189, "total": 198 }, "high_school_government_and_politics": { "accuracy": 97.93, "correct": 189, "total": 193 }, "high_school_macroeconomics": { "accuracy": 95.38, "correct": 372, "total": 390 }, "high_school_mathematics": { "accuracy": 95.56, "correct": 258, "total": 270 }, "high_school_microeconomics": { "accuracy": 97.48, "correct": 232, "total": 238 }, "high_school_physics": { "accuracy": 92.05, "correct": 139, "total": 151 }, "high_school_psychology": { "accuracy": 96.15, "correct": 524, "total": 545 }, "high_school_statistics": { "accuracy": 94.44, "correct": 204, "total": 216 }, "high_school_us_history": { "accuracy": 95.59, "correct": 195, "total": 204 }, "high_school_world_history": { "accuracy": 93.67, "correct": 222, "total": 237 }, "human_aging": { "accuracy": 84.3, "correct": 188, "total": 223 }, "human_sexuality": { "accuracy": 91.6, "correct": 120, "total": 131 }, "international_law": { "accuracy": 92.56, "correct": 112, "total": 121 }, "jurisprudence": { "accuracy": 89.81, "correct": 97, "total": 108 }, "logical_fallacies": { "accuracy": 90.8, "correct": 148, "total": 163 }, "machine_learning": { "accuracy": 89.29, "correct": 100, "total": 112 }, "management": { "accuracy": 91.26, "correct": 94, "total": 103 }, "marketing": { "accuracy": 95.73, "correct": 224, "total": 234 }, "medical_genetics": { "accuracy": 100.0, "correct": 100, "total": 100 }, "miscellaneous": { "accuracy": 97.19, "correct": 761, "total": 783 }, "moral_disputes": { "accuracy": 86.42, "correct": 299, "total": 346 }, "moral_scenarios": { "accuracy": 86.93, "correct": 778, "total": 895 }, "nutrition": { "accuracy": 94.77, "correct": 290, "total": 306 }, "philosophy": { "accuracy": 92.28, "correct": 287, "total": 311 }, "prehistory": { "accuracy": 94.44, "correct": 306, "total": 324 }, "professional_accounting": { "accuracy": 96.1, "correct": 271, "total": 282 }, "professional_law": { "accuracy": 78.29, "correct": 1201, "total": 1534 }, "professional_medicine": { "accuracy": 95.96, "correct": 261, "total": 272 }, "professional_psychology": { "accuracy": 93.95, "correct": 575, "total": 612 }, "public_relations": { "accuracy": 81.82, "correct": 90, "total": 110 }, "security_studies": { "accuracy": 80.0, "correct": 196, "total": 245 }, "sociology": { "accuracy": 94.03, "correct": 189, "total": 201 }, "us_foreign_policy": { "accuracy": 96.0, "correct": 96, "total": 100 }, "virology": { "accuracy": 54.22, "correct": 90, "total": 166 }, "world_religions": { "accuracy": 91.23, "correct": 156, "total": 171 } } }, { "name": "opencompass.models.OpenAI_app_gpt-5.5", "total_questions": 14042, "total_correct": 13177, "overall_accuracy": 93.8399088448939, "datasets": { "abstract_algebra": { "accuracy": 96.0, "correct": 96, "total": 100 }, "anatomy": { "accuracy": 91.85, "correct": 124, "total": 135 }, "astronomy": { "accuracy": 98.03, "correct": 149, "total": 152 }, "business_ethics": { "accuracy": 84.0, "correct": 84, "total": 100 }, "clinical_knowledge": { "accuracy": 96.23, "correct": 255, "total": 265 }, "college_biology": { "accuracy": 99.31, "correct": 143, "total": 144 }, "college_chemistry": { "accuracy": 76.0, "correct": 76, "total": 100 }, "college_computer_science": { "accuracy": 97.0, "correct": 97, "total": 100 }, "college_mathematics": { "accuracy": 99.0, "correct": 99, "total": 100 }, "college_medicine": { "accuracy": 89.6, "correct": 155, "total": 173 }, "college_physics": { "accuracy": 100.0, "correct": 102, "total": 102 }, "computer_security": { "accuracy": 93.0, "correct": 93, "total": 100 }, "conceptual_physics": { "accuracy": 96.6, "correct": 227, "total": 235 }, "econometrics": { "accuracy": 85.96, "correct": 98, "total": 114 }, "electrical_engineering": { "accuracy": 93.79, "correct": 136, "total": 145 }, "elementary_mathematics": { "accuracy": 98.41, "correct": 372, "total": 378 }, "formal_logic": { "accuracy": 96.03, "correct": 121, "total": 126 }, "global_facts": { "accuracy": 85.0, "correct": 85, "total": 100 }, "high_school_biology": { "accuracy": 96.13, "correct": 298, "total": 310 }, "high_school_chemistry": { "accuracy": 95.57, "correct": 194, "total": 203 }, "high_school_computer_science": { "accuracy": 97.0, "correct": 97, "total": 100 }, "high_school_european_history": { "accuracy": 92.12, "correct": 152, "total": 165 }, "high_school_geography": { "accuracy": 94.44, "correct": 187, "total": 198 }, "high_school_government_and_politics": { "accuracy": 98.45, "correct": 190, "total": 193 }, "high_school_macroeconomics": { "accuracy": 96.92, "correct": 378, "total": 390 }, "high_school_mathematics": { "accuracy": 99.26, "correct": 268, "total": 270 }, "high_school_microeconomics": { "accuracy": 98.32, "correct": 234, "total": 238 }, "high_school_physics": { "accuracy": 95.36, "correct": 144, "total": 151 }, "high_school_psychology": { "accuracy": 97.06, "correct": 529, "total": 545 }, "high_school_statistics": { "accuracy": 96.76, "correct": 209, "total": 216 }, "high_school_us_history": { "accuracy": 96.08, "correct": 196, "total": 204 }, "high_school_world_history": { "accuracy": 97.47, "correct": 231, "total": 237 }, "human_aging": { "accuracy": 87.89, "correct": 196, "total": 223 }, "human_sexuality": { "accuracy": 94.66, "correct": 124, "total": 131 }, "international_law": { "accuracy": 92.56, "correct": 112, "total": 121 }, "jurisprudence": { "accuracy": 94.44, "correct": 102, "total": 108 }, "logical_fallacies": { "accuracy": 93.25, "correct": 152, "total": 163 }, "machine_learning": { "accuracy": 91.96, "correct": 103, "total": 112 }, "management": { "accuracy": 92.23, "correct": 95, "total": 103 }, "marketing": { "accuracy": 96.15, "correct": 225, "total": 234 }, "medical_genetics": { "accuracy": 98.0, "correct": 98, "total": 100 }, "miscellaneous": { "accuracy": 98.34, "correct": 770, "total": 783 }, "moral_disputes": { "accuracy": 89.31, "correct": 309, "total": 346 }, "moral_scenarios": { "accuracy": 91.84, "correct": 822, "total": 895 }, "nutrition": { "accuracy": 95.75, "correct": 293, "total": 306 }, "philosophy": { "accuracy": 96.14, "correct": 299, "total": 311 }, "prehistory": { "accuracy": 95.99, "correct": 311, "total": 324 }, "professional_accounting": { "accuracy": 97.52, "correct": 275, "total": 282 }, "professional_law": { "accuracy": 89.11, "correct": 1367, "total": 1534 }, "professional_medicine": { "accuracy": 98.16, "correct": 267, "total": 272 }, "professional_psychology": { "accuracy": 95.42, "correct": 584, "total": 612 }, "public_relations": { "accuracy": 83.64, "correct": 92, "total": 110 }, "security_studies": { "accuracy": 88.16, "correct": 216, "total": 245 }, "sociology": { "accuracy": 95.52, "correct": 192, "total": 201 }, "us_foreign_policy": { "accuracy": 96.0, "correct": 96, "total": 100 }, "virology": { "accuracy": 57.23, "correct": 95, "total": 166 }, "world_religions": { "accuracy": 95.32, "correct": 163, "total": 171 } } }, { "name": "opencompass.models.OpenAI_app_whalezeAI3.0", "total_questions": 14042, "total_correct": 12357, "overall_accuracy": 88.0002848597066, "datasets": { "abstract_algebra": { "accuracy": 80.0, "correct": 80, "total": 100 }, "anatomy": { "accuracy": 89.62962962962962, "correct": 121, "total": 135 }, "astronomy": { "accuracy": 94.73684210526315, "correct": 144, "total": 152 }, "business_ethics": { "accuracy": 86.0, "correct": 86, "total": 100 }, "clinical_knowledge": { "accuracy": 93.58490566037736, "correct": 248, "total": 265 }, "college_biology": { "accuracy": 98.61111111111111, "correct": 142, "total": 144 }, "college_chemistry": { "accuracy": 64.0, "correct": 64, "total": 100 }, "college_computer_science": { "accuracy": 85.0, "correct": 85, "total": 100 }, "college_mathematics": { "accuracy": 83.0, "correct": 83, "total": 100 }, "college_medicine": { "accuracy": 86.70520231213872, "correct": 150, "total": 173 }, "college_physics": { "accuracy": 94.11764705882352, "correct": 96, "total": 102 }, "computer_security": { "accuracy": 85.0, "correct": 85, "total": 100 }, "conceptual_physics": { "accuracy": 93.19148936170212, "correct": 219, "total": 235 }, "econometrics": { "accuracy": 82.45614035087719, "correct": 94, "total": 114 }, "electrical_engineering": { "accuracy": 88.27586206896552, "correct": 128, "total": 145 }, "elementary_mathematics": { "accuracy": 93.38624338624338, "correct": 353, "total": 378 }, "formal_logic": { "accuracy": 79.36507936507937, "correct": 100, "total": 126 }, "global_facts": { "accuracy": 72.0, "correct": 72, "total": 100 }, "high_school_biology": { "accuracy": 95.48387096774194, "correct": 296, "total": 310 }, "high_school_chemistry": { "accuracy": 86.20689655172413, "correct": 175, "total": 203 }, "high_school_computer_science": { "accuracy": 91.0, "correct": 91, "total": 100 }, "high_school_european_history": { "accuracy": 89.6969696969697, "correct": 148, "total": 165 }, "high_school_geography": { "accuracy": 93.43434343434343, "correct": 185, "total": 198 }, "high_school_government_and_politics": { "accuracy": 96.89119170984456, "correct": 187, "total": 193 }, "high_school_macroeconomics": { "accuracy": 93.33333333333333, "correct": 364, "total": 390 }, "high_school_mathematics": { "accuracy": 81.11111111111111, "correct": 219, "total": 270 }, "high_school_microeconomics": { "accuracy": 97.05882352941177, "correct": 231, "total": 238 }, "high_school_physics": { "accuracy": 86.09271523178808, "correct": 130, "total": 151 }, "high_school_psychology": { "accuracy": 95.96330275229357, "correct": 523, "total": 545 }, "high_school_statistics": { "accuracy": 85.64814814814815, "correct": 185, "total": 216 }, "high_school_us_history": { "accuracy": 95.09803921568627, "correct": 194, "total": 204 }, "high_school_world_history": { "accuracy": 93.67088607594937, "correct": 222, "total": 237 }, "human_aging": { "accuracy": 86.09865470852019, "correct": 192, "total": 223 }, "human_sexuality": { "accuracy": 93.12977099236642, "correct": 122, "total": 131 }, "international_law": { "accuracy": 90.9090909090909, "correct": 110, "total": 121 }, "jurisprudence": { "accuracy": 89.81481481481481, "correct": 97, "total": 108 }, "logical_fallacies": { "accuracy": 96.31901840490798, "correct": 157, "total": 163 }, "machine_learning": { "accuracy": 88.39285714285714, "correct": 99, "total": 112 }, "management": { "accuracy": 93.20388349514563, "correct": 96, "total": 103 }, "marketing": { "accuracy": 96.58119658119658, "correct": 226, "total": 234 }, "medical_genetics": { "accuracy": 98.0, "correct": 98, "total": 100 }, "miscellaneous": { "accuracy": 97.57343550446998, "correct": 764, "total": 783 }, "moral_disputes": { "accuracy": 87.28323699421965, "correct": 302, "total": 346 }, "moral_scenarios": { "accuracy": 82.01117318435755, "correct": 734, "total": 895 }, "nutrition": { "accuracy": 92.48366013071896, "correct": 283, "total": 306 }, "philosophy": { "accuracy": 90.35369774919614, "correct": 281, "total": 311 }, "prehistory": { "accuracy": 92.90123456790124, "correct": 301, "total": 324 }, "professional_accounting": { "accuracy": 87.94326241134752, "correct": 248, "total": 282 }, "professional_law": { "accuracy": 72.6857887874837, "correct": 1115, "total": 1534 }, "professional_medicine": { "accuracy": 94.85294117647058, "correct": 258, "total": 272 }, "professional_psychology": { "accuracy": 89.54248366013073, "correct": 548, "total": 612 }, "public_relations": { "accuracy": 76.36363636363637, "correct": 84, "total": 110 }, "security_studies": { "accuracy": 86.12244897959184, "correct": 211, "total": 245 }, "sociology": { "accuracy": 94.02985074626866, "correct": 189, "total": 201 }, "us_foreign_policy": { "accuracy": 95.0, "correct": 95, "total": 100 }, "virology": { "accuracy": 54.81927710843374, "correct": 91, "total": 166 }, "world_religions": { "accuracy": 91.22807017543859, "correct": 156, "total": 171 } } }, { "name": "claude-opus-4-8", "total_questions": 14042, "total_correct": 12719, "overall_accuracy": 90.57826520438684, "datasets": { "abstract_algebra": { "accuracy": 90.0, "correct": 90, "total": 100 }, "anatomy": { "accuracy": 92.59, "correct": 125, "total": 135 }, "astronomy": { "accuracy": 95.39, "correct": 145, "total": 152 }, "business_ethics": { "accuracy": 84.0, "correct": 84, "total": 100 }, "clinical_knowledge": { "accuracy": 94.72, "correct": 251, "total": 265 }, "college_biology": { "accuracy": 97.92, "correct": 141, "total": 144 }, "college_chemistry": { "accuracy": 71.0, "correct": 71, "total": 100 }, "college_computer_science": { "accuracy": 94.0, "correct": 94, "total": 100 }, "college_mathematics": { "accuracy": 81.0, "correct": 81, "total": 100 }, "college_medicine": { "accuracy": 91.91, "correct": 159, "total": 173 }, "college_physics": { "accuracy": 94.12, "correct": 96, "total": 102 }, "computer_security": { "accuracy": 93.0, "correct": 93, "total": 100 }, "conceptual_physics": { "accuracy": 94.04, "correct": 221, "total": 235 }, "econometrics": { "accuracy": 84.21, "correct": 96, "total": 114 }, "electrical_engineering": { "accuracy": 91.72, "correct": 133, "total": 145 }, "elementary_mathematics": { "accuracy": 95.24, "correct": 360, "total": 378 }, "formal_logic": { "accuracy": 84.92, "correct": 107, "total": 126 }, "global_facts": { "accuracy": 70.0, "correct": 70, "total": 100 }, "high_school_biology": { "accuracy": 95.81, "correct": 297, "total": 310 }, "high_school_chemistry": { "accuracy": 91.63, "correct": 186, "total": 203 }, "high_school_computer_science": { "accuracy": 96.0, "correct": 96, "total": 100 }, "high_school_european_history": { "accuracy": 87.88, "correct": 145, "total": 165 }, "high_school_geography": { "accuracy": 94.44, "correct": 187, "total": 198 }, "high_school_government_and_politics": { "accuracy": 97.41, "correct": 188, "total": 193 }, "high_school_macroeconomics": { "accuracy": 95.38, "correct": 372, "total": 390 }, "high_school_mathematics": { "accuracy": 85.19, "correct": 230, "total": 270 }, "high_school_microeconomics": { "accuracy": 97.48, "correct": 232, "total": 238 }, "high_school_physics": { "accuracy": 90.73, "correct": 137, "total": 151 }, "high_school_psychology": { "accuracy": 96.15, "correct": 524, "total": 545 }, "high_school_statistics": { "accuracy": 93.52, "correct": 202, "total": 216 }, "high_school_us_history": { "accuracy": 96.57, "correct": 197, "total": 204 }, "high_school_world_history": { "accuracy": 97.05, "correct": 230, "total": 237 }, "human_aging": { "accuracy": 84.3, "correct": 188, "total": 223 }, "human_sexuality": { "accuracy": 92.37, "correct": 121, "total": 131 }, "international_law": { "accuracy": 90.08, "correct": 109, "total": 121 }, "jurisprudence": { "accuracy": 94.44, "correct": 102, "total": 108 }, "logical_fallacies": { "accuracy": 92.64, "correct": 151, "total": 163 }, "machine_learning": { "accuracy": 93.75, "correct": 105, "total": 112 }, "management": { "accuracy": 94.17, "correct": 97, "total": 103 }, "marketing": { "accuracy": 95.73, "correct": 224, "total": 234 }, "medical_genetics": { "accuracy": 98.0, "correct": 98, "total": 100 }, "miscellaneous": { "accuracy": 96.55, "correct": 756, "total": 783 }, "moral_disputes": { "accuracy": 86.42, "correct": 299, "total": 346 }, "moral_scenarios": { "accuracy": 84.36, "correct": 755, "total": 895 }, "nutrition": { "accuracy": 93.14, "correct": 285, "total": 306 }, "philosophy": { "accuracy": 92.28, "correct": 287, "total": 311 }, "prehistory": { "accuracy": 96.91, "correct": 314, "total": 324 }, "professional_accounting": { "accuracy": 92.2, "correct": 260, "total": 282 }, "professional_law": { "accuracy": 82.46, "correct": 1265, "total": 1534 }, "professional_medicine": { "accuracy": 96.69, "correct": 263, "total": 272 }, "professional_psychology": { "accuracy": 92.81, "correct": 568, "total": 612 }, "public_relations": { "accuracy": 73.64, "correct": 81, "total": 110 }, "security_studies": { "accuracy": 87.76, "correct": 215, "total": 245 }, "sociology": { "accuracy": 94.53, "correct": 190, "total": 201 }, "us_foreign_policy": { "accuracy": 95.0, "correct": 95, "total": 100 }, "virology": { "accuracy": 54.82, "correct": 91, "total": 166 }, "world_religions": { "accuracy": 93.57, "correct": 160, "total": 171 } } }, { "name": "kimi-k2.6", "total_questions": 14042, "total_correct": 11861, "overall_accuracy": 84.46802449793476, "datasets": { "abstract_algebra": { "accuracy": 83.0, "correct": 83, "total": 100 }, "anatomy": { "accuracy": 87.41, "correct": 118, "total": 135 }, "astronomy": { "accuracy": 92.76, "correct": 141, "total": 152 }, "business_ethics": { "accuracy": 78.0, "correct": 78, "total": 100 }, "clinical_knowledge": { "accuracy": 90.57, "correct": 240, "total": 265 }, "college_biology": { "accuracy": 95.14, "correct": 137, "total": 144 }, "college_chemistry": { "accuracy": 70.0, "correct": 70, "total": 100 }, "college_computer_science": { "accuracy": 83.0, "correct": 83, "total": 100 }, "college_mathematics": { "accuracy": 78.0, "correct": 78, "total": 100 }, "college_medicine": { "accuracy": 80.92, "correct": 140, "total": 173 }, "college_physics": { "accuracy": 91.18, "correct": 93, "total": 102 }, "computer_security": { "accuracy": 85.0, "correct": 85, "total": 100 }, "conceptual_physics": { "accuracy": 94.89, "correct": 223, "total": 235 }, "econometrics": { "accuracy": 70.18, "correct": 80, "total": 114 }, "electrical_engineering": { "accuracy": 84.14, "correct": 122, "total": 145 }, "elementary_mathematics": { "accuracy": 97.09, "correct": 367, "total": 378 }, "formal_logic": { "accuracy": 83.33, "correct": 105, "total": 126 }, "global_facts": { "accuracy": 71.0, "correct": 71, "total": 100 }, "high_school_biology": { "accuracy": 92.26, "correct": 286, "total": 310 }, "high_school_chemistry": { "accuracy": 88.18, "correct": 179, "total": 203 }, "high_school_computer_science": { "accuracy": 94.0, "correct": 94, "total": 100 }, "high_school_european_history": { "accuracy": 89.09, "correct": 147, "total": 165 }, "high_school_geography": { "accuracy": 91.41, "correct": 181, "total": 198 }, "high_school_government_and_politics": { "accuracy": 96.89, "correct": 187, "total": 193 }, "high_school_macroeconomics": { "accuracy": 93.33, "correct": 364, "total": 390 }, "high_school_mathematics": { "accuracy": 88.89, "correct": 240, "total": 270 }, "high_school_microeconomics": { "accuracy": 94.96, "correct": 226, "total": 238 }, "high_school_physics": { "accuracy": 88.74, "correct": 134, "total": 151 }, "high_school_psychology": { "accuracy": 95.23, "correct": 519, "total": 545 }, "high_school_statistics": { "accuracy": 84.72, "correct": 183, "total": 216 }, "high_school_us_history": { "accuracy": 90.69, "correct": 185, "total": 204 }, "high_school_world_history": { "accuracy": 92.41, "correct": 219, "total": 237 }, "human_aging": { "accuracy": 84.3, "correct": 188, "total": 223 }, "human_sexuality": { "accuracy": 92.37, "correct": 121, "total": 131 }, "international_law": { "accuracy": 89.26, "correct": 108, "total": 121 }, "jurisprudence": { "accuracy": 87.04, "correct": 94, "total": 108 }, "logical_fallacies": { "accuracy": 92.02, "correct": 150, "total": 163 }, "machine_learning": { "accuracy": 81.25, "correct": 91, "total": 112 }, "management": { "accuracy": 93.2, "correct": 96, "total": 103 }, "marketing": { "accuracy": 96.15, "correct": 225, "total": 234 }, "medical_genetics": { "accuracy": 95.0, "correct": 95, "total": 100 }, "miscellaneous": { "accuracy": 96.17, "correct": 753, "total": 783 }, "moral_disputes": { "accuracy": 82.95, "correct": 287, "total": 346 }, "moral_scenarios": { "accuracy": 79.89, "correct": 715, "total": 895 }, "nutrition": { "accuracy": 90.85, "correct": 278, "total": 306 }, "philosophy": { "accuracy": 89.39, "correct": 278, "total": 311 }, "prehistory": { "accuracy": 90.74, "correct": 294, "total": 324 }, "professional_accounting": { "accuracy": 87.59, "correct": 247, "total": 282 }, "professional_law": { "accuracy": 51.76, "correct": 794, "total": 1534 }, "professional_medicine": { "accuracy": 87.87, "correct": 239, "total": 272 }, "professional_psychology": { "accuracy": 88.73, "correct": 543, "total": 612 }, "public_relations": { "accuracy": 73.64, "correct": 81, "total": 110 }, "security_studies": { "accuracy": 80.0, "correct": 196, "total": 245 }, "sociology": { "accuracy": 92.54, "correct": 186, "total": 201 }, "us_foreign_policy": { "accuracy": 94.0, "correct": 94, "total": 100 }, "virology": { "accuracy": 57.83, "correct": 96, "total": 166 }, "world_religions": { "accuracy": 90.06, "correct": 154, "total": 171 } } }, { "name": "glm-5.2", "total_questions": 14042, "total_correct": 12184, "overall_accuracy": 86.76826662868538, "datasets": { "abstract_algebra": { "accuracy": 90.0, "correct": 90, "total": 100 }, "anatomy": { "accuracy": 87.41, "correct": 118, "total": 135 }, "astronomy": { "accuracy": 94.08, "correct": 143, "total": 152 }, "business_ethics": { "accuracy": 79.0, "correct": 79, "total": 100 }, "clinical_knowledge": { "accuracy": 90.19, "correct": 239, "total": 265 }, "college_biology": { "accuracy": 95.83, "correct": 138, "total": 144 }, "college_chemistry": { "accuracy": 78.0, "correct": 78, "total": 100 }, "college_computer_science": { "accuracy": 91.0, "correct": 91, "total": 100 }, "college_mathematics": { "accuracy": 83.0, "correct": 83, "total": 100 }, "college_medicine": { "accuracy": 84.39, "correct": 146, "total": 173 }, "college_physics": { "accuracy": 96.08, "correct": 98, "total": 102 }, "computer_security": { "accuracy": 83.0, "correct": 83, "total": 100 }, "conceptual_physics": { "accuracy": 94.47, "correct": 222, "total": 235 }, "econometrics": { "accuracy": 78.07, "correct": 89, "total": 114 }, "electrical_engineering": { "accuracy": 88.97, "correct": 129, "total": 145 }, "elementary_mathematics": { "accuracy": 98.15, "correct": 371, "total": 378 }, "formal_logic": { "accuracy": 91.27, "correct": 115, "total": 126 }, "global_facts": { "accuracy": 66.0, "correct": 66, "total": 100 }, "high_school_biology": { "accuracy": 93.87, "correct": 291, "total": 310 }, "high_school_chemistry": { "accuracy": 92.61, "correct": 188, "total": 203 }, "high_school_computer_science": { "accuracy": 95.0, "correct": 95, "total": 100 }, "high_school_european_history": { "accuracy": 86.67, "correct": 143, "total": 165 }, "high_school_geography": { "accuracy": 93.94, "correct": 186, "total": 198 }, "high_school_government_and_politics": { "accuracy": 97.41, "correct": 188, "total": 193 }, "high_school_macroeconomics": { "accuracy": 92.31, "correct": 360, "total": 390 }, "high_school_mathematics": { "accuracy": 91.11, "correct": 246, "total": 270 }, "high_school_microeconomics": { "accuracy": 95.8, "correct": 228, "total": 238 }, "high_school_physics": { "accuracy": 88.74, "correct": 134, "total": 151 }, "high_school_psychology": { "accuracy": 94.86, "correct": 517, "total": 545 }, "high_school_statistics": { "accuracy": 89.35, "correct": 193, "total": 216 }, "high_school_us_history": { "accuracy": 91.67, "correct": 187, "total": 204 }, "high_school_world_history": { "accuracy": 90.3, "correct": 214, "total": 237 }, "human_aging": { "accuracy": 80.72, "correct": 180, "total": 223 }, "human_sexuality": { "accuracy": 88.55, "correct": 116, "total": 131 }, "international_law": { "accuracy": 91.74, "correct": 111, "total": 121 }, "jurisprudence": { "accuracy": 87.96, "correct": 95, "total": 108 }, "logical_fallacies": { "accuracy": 87.73, "correct": 143, "total": 163 }, "machine_learning": { "accuracy": 86.61, "correct": 97, "total": 112 }, "management": { "accuracy": 87.38, "correct": 90, "total": 103 }, "marketing": { "accuracy": 91.88, "correct": 215, "total": 234 }, "medical_genetics": { "accuracy": 97.0, "correct": 97, "total": 100 }, "miscellaneous": { "accuracy": 96.17, "correct": 753, "total": 783 }, "moral_disputes": { "accuracy": 80.92, "correct": 280, "total": 346 }, "moral_scenarios": { "accuracy": 79.44, "correct": 711, "total": 895 }, "nutrition": { "accuracy": 89.87, "correct": 275, "total": 306 }, "philosophy": { "accuracy": 84.57, "correct": 263, "total": 311 }, "prehistory": { "accuracy": 91.05, "correct": 295, "total": 324 }, "professional_accounting": { "accuracy": 92.55, "correct": 261, "total": 282 }, "professional_law": { "accuracy": 69.56, "correct": 1067, "total": 1534 }, "professional_medicine": { "accuracy": 87.87, "correct": 239, "total": 272 }, "professional_psychology": { "accuracy": 90.03, "correct": 551, "total": 612 }, "public_relations": { "accuracy": 74.55, "correct": 82, "total": 110 }, "security_studies": { "accuracy": 75.51, "correct": 185, "total": 245 }, "sociology": { "accuracy": 93.03, "correct": 187, "total": 201 }, "us_foreign_policy": { "accuracy": 92.0, "correct": 92, "total": 100 }, "virology": { "accuracy": 54.82, "correct": 91, "total": 166 }, "world_religions": { "accuracy": 93.57, "correct": 160, "total": 171 } } } ] }