Treatment Outcome Prediction on TheraPhase (test) benchmark leaderboard · SOTA2 Research

Treatment Outcome Prediction on TheraPhase (test)

69.58AccuracyLlama3.1-405B

Evaluation Results

Method	Links
Llama3.1-405B2024.10		69.58	79.65	79.89	79.76	59.25	69.51
Mistral-8X7B2024.10		68.25	74.69	87.22	80.46	47.79	64.13
GPT-4-turbo2024.10		68	78.24	79.44	78.83	56.6	67.72
Qwen2-72B2024.10		67.25	77.47	79.44	78.44	55.15	66.79
Llama3.1-70B2024.10		67.08	77.96	78.22	78.09	55.97	67.03
Mistral-8X22B2024.10		63.83	75.44	76.78	76.1	50.89	63.5
GPT-4o2024.10		63.75	77.06	73.56	75.26	53.7	64.48
GPT-4o-mini2024.10		63.17	77.27	72.11	74.59	53.8	64.2