Automated Health Data Modeling on AutoHealth Evaluation Benchmark Tasks T1-T17 benchmark leaderboard · SOTA2 Research

Automated Health Data Modeling on AutoHealth Evaluation Benchmark Tasks T1-T17

100T1 ScoreClaude Code

Evaluation Results

Method	Links
Claude Code2026.02		100	100	100	100	100	100	100	100	100	100	100	100	100	100	100	100	100	100
AutoHealth2026.02		100	100	100	100	100	100	100	100	100	100	100	100	100	100	100	100	100	100
AutoHealth2026.02		88.3	87.3	87.5	89.8	89.4	84.7	97.1	87.9	84.4	75.5	61.5	71.3	90.7	85	84.9	81.6	81.2	84
AutoML-Agent2026.02		80.5	92.7	44.8	61.7	66.3	34.9	85.2	0	0	0	0	11	91.4	84.1	0	0	0	38.4
AutoHealth2026.02		79.3	92	61.3	61.7	64.6	71.7	96.9	82.2	87	63.2	11.7	54.3	98.2	81.1	83.8	83.5	96.5	74.7
Claude Code2026.02		79.1	81.7	78.6	73	68.5	65.2	70.5	82.5	94.2	71.5	61.8	58.7	89.3	76.8	78.3	73.7	65.9	74.7
Claude Code2026.02		76.6	82.8	37.3	61.3	63.7	33.5	53.1	79.9	95.2	39.8	10.7	12.5	94.3	75	79.2	65.5	21.5	57.8
AutoHealth2026.02		76.5	74.6	75.1	79.5	78.7	69.4	94.3	75.7	68.8	50.9	23.1	42.5	81.4	70	69.7	63.3	62.4	68
DS-Agent2026.02		71.9	88.2	0	61	60.2	0	0	0	86.2	0	0	12.8	84.2	59.1	0	0	0	30.8
Claude Code2026.02		58.2	63.4	57.1	46.1	36.9	30.5	41.1	64.9	88.3	43	23.6	17.3	78.7	53.6	56.5	47.4	31.7	49.3
DS-Agent2026.02		50	50	0	50	50	0	0	0	50	0	0	50	50	50	0	0	0	23.5
AutoML-Agent2026.02		50	50	50	50	50	50	50	0	50	0	0	50	50	50	0	0	0	32.4
AutoML-Agent2026.02		45.1	48.2	36.2	40.4	41.6	33.7	46.3	0	25	0	0	27.8	47.9	46	0	0	0	25.8
DS-Agent2026.02		43	47.1	0	40.2	40.1	0	0	0	46.6	0	0	28.2	46.1	39.8	0	0	0	19.5
AutoML-Agent2026.02		40.3	46.3	22.5	30.8	33.1	17.5	42.6	0	0	0	0	5.5	45.7	42	0	0	0	19.2
DS-Agent2026.02		36	44.1	0	30.5	30.1	0	0	0	43.1	0	0	6.4	42.1	29.5	0	0	0	15.4
LLM2026.02		0	0	0	100	0	0	50	0	50	0	0	100	50	50	0	0	0	23.5
LLM2026.02		0	0	0	69.6	0	0	39.2	0	42.4	0	0	13.7	42.9	28.6	0	0	0	13.9
LLM2026.02		0	0	0	54.6	0	0	78.4	0	84.8	0	0	10.8	85.7	57.1	0	0	0	21.8
LLM2026.02		0	0	0	84.8	0	0	44.6	0	46.2	0	0	56.8	46.4	39.3	0	0	0	18.7