Fine-grained Classification on Resistance behavior dataset 5-fold CV (test) benchmark leaderboard · SOTA2 Research

Fine-grained Classification on Resistance behavior dataset 5-fold CV (test)

67.02Fine-grained Overall PrecisionPsyFIRE

Evaluation Results

Method	Links
PsyFIRE2026.01		67.02	66.76	66.58	67.72	92.14	92.73	92.43	90.47	89.69	90.07
Claude-3.5-Sonnet2026.01		49.69	46.19	43.65	46.87	76.84	95.58	85.19	91.58	62.51	74.3
Claude-3.5-Sonnet2026.01		49.45	46.24	44.99	47.89	80.2	91.26	85.37	86.16	70.67	77.63
GPT-4o2026.01		49	49.79	45.37	47.84	77.96	94.85	85.57	90.71	65.06	75.73
GPT-4o2026.01		48.01	49.74	45.22	47.62	76.66	93.7	84.33	88.47	62.86	73.49
Llama-3.1-70B-Instruct2026.01		47.69	41.71	39.25	41.24	81.27	79.78	80.42	74.43	75.86	75.01
Llama-3.1-70B-Instruct2026.01		47.61	35.76	32.91	34.64	77.78	83.71	80.64	76.47	68.88	72.47
Llama-3.1-8B-Instruct2026.01		40.65	27.02	27.14	29.54	74.59	85.38	78.49	80.11	59.56	65.72
Qwen2.5-72B-Instruct2026.01		40.44	40.51	36.44	39.49	76.54	85.18	80.63	77.38	66.01	71.24
Qwen2.5-14B-Instruct2026.01		39.57	31.1	25.06	27.81	73.43	89.3	79.93	83.51	56.18	65.23
Qwen2.5-72B-Instruct2026.01		39.28	41.42	36.47	40.2	81.44	78.39	79.76	73.32	76.44	74.68
Qwen2.5-32B-Instruct2026.01		38.48	40.92	32.76	34.99	76.74	83.49	79.53	77.12	66.15	70.27
Qwen2.5-14B-Instruct2026.01		38.08	32.54	25.92	30.49	73.82	88.54	79.97	82.24	57.67	66.14
Qwen2.5-32B-Instruct2026.01		37.64	39.01	30.76	32.97	74.77	87.09	79.73	81.51	59.9	67.01
Qwen2.5-7B-Instruct2026.01		33.39	23.08	21.21	23.76	68.87	95.99	80.2	89.33	43.51	58.49
Llama-3.1-8B-Instruct2026.01		29.27	28.98	26.19	28.83	62.82	85.35	72.07	84.76	60.27	69.85
Qwen2.5-7B-Instruct2026.01		29.12	28.01	24.25	27.75	69.43	96.12	80.63	89.91	44.95	59.94