Taxonomy Generation on Ancient Chinese Cultural System 1.0 (test) benchmark leaderboard · SOTA2 Research

Taxonomy Generation on Ancient Chinese Cultural System 1.0 (test)

100Path GranularityGPT-4o

Evaluation Results

Method	Links
GPT-4o2026.01		100	0.3931	27.47	33.33	49.15	-0.0952
GPT-4o2026.01		98.96	0.2973	30.82	53.33	53.85	-0.0326
GPT-4o2026.01		97.5	0.259	37.52	48.89	36.36	-0.0331
Qwen32026.01		95.83	0.2566	35.68	43.33	59.62	-0.0197
DeepSeek-V32026.01		95.4	0.1366	39.87	43.33	54.74	-0.0318
Qwen32026.01		93.55	0.1213	46.23	48.89	59.22	0.0174
CHisAgent2026.01		91.54	0.2784	75.13	68.89	77.7	0.1887
Qwen32026.01		88.75	0.2356	33.67	36.67	59.09	-0.0379
Chain-of-Layer2026.01		80.99	0.2479	43.72	46.67	50.69	0.0104
CHED2026.01		80.25	0.1432	45.39	—	—	—
DeepSeek-V32026.01		79.8	0.1485	61.81	53.33	66.99	0.0769
DeepSeek-V32026.01		76.56	0.1556	41.29	42.22	44.93	-0.0211
TaxoAdapt2026.01		70.98	0.2075	74.17	60	69.21	0.3927