Reasoning in IoT (RIT) Classification on Mutation Dataset (Experiment A) benchmark leaderboard · SOTA2 Research

Reasoning in IoT (RIT) Classification on Mutation Dataset (Experiment A)

82.06WACLlama-8b

Evaluation Results

Method	Links
Llama-8b2026.01		82.06	19.95	83.56	11.49	41.25	4.15	35.19
Deepseek-r1-7b2026.01		80.4	21.81	8.72	45.4	24.4	24.62	30.42
Deepseek-r1-7b2026.01		76.08	36.17	22.15	31.61	30.02	24.07	33.95
Deepseek-r1-7b2026.01		76.08	13.83	11.74	35.06	19.1	25.73	27.33
Llama-8b2026.01		74.42	36.44	75.17	22.41	57.78	12.17	42.97
Llama-70b2026.01		72.43	9.84	35.91	13.79	53.13	2.07	29.34
Llama-8b2026.01		60.13	24.47	74.5	12.64	63.72	8.85	39.2
Gemini-1.5-Pro2026.01		42.86	39.36	87.25	81.03	41.89	51.73	52.63
Llama-70b2026.01		37.87	19.68	30.54	20.11	26.48	2.35	19.88
Gemini-1.5-Pro2026.01		36.21	55.32	76.85	80.46	49.76	63.35	58.28
Gemini-1.5-Pro2026.01		35.88	60.11	19.13	89.08	48.31	57.95	50.74
Llama-70b2026.01		17.61	4.79	31.21	12.64	29.37	2.77	15.59