Our new X account is live! Follow @wizwand_team for updates

Interactive Science Simulation on ScienceWorld v1.0 (test)

97.04Task 1-1 (L) Score

SwiftSage

Updated 4d ago

Evaluation Results

Method	Links
SwiftSage 2023.05		97.04	87.04	72.78	100	99.17	88.17	95.73	88.67	55.33	71.9	77.86	100	100	91.67	100	74.59	93.93	49.4	100	91.48	95	85	93.33	89	68.5	75	70	60	92.3	77.6	92.22	77.79	83	84.68
SayCan 2023.05		33.06	10.39	3.88	0.37	26.37	8.03	17.41	52.14	22.5	99.56	47.76	22.87	58.18	20.87	31.43	9.92	13.93	47.81	39.26	19.72	80	67.5	50	20.91	16	21.94	32.26	13.67	67.53	59.45	43.83	36.58	23.65	33.82
Reflexion 2023.05		4.22	10.61	7.78	0.92	5.92	28.59	22.37	100	17.45	72.54	70.22	64.93	87.27	16.42	100	7.33	13	70.35	70.67	15.77	100	84.37	83	2.58	8	50.63	100	70.62	50.9	23.69	71.47	35.43	30.17	45.34
DRRN 2023.05		3.52	3.52	0	0	6.56	5.5	6	12	9	9.05	9.52	15	45	21.67	19.17	8	14.29	15.77	26.67	10.37	50	50	33.33	21	8	10	10	10	16.8	17	28.08	10.85	8.26	15.56
ReAct 2023.05		3.52	13.7	7.78	9.88	7.19	6.1	22.37	56	54.33	76.19	88.81	26.67	80	53.33	27.5	9.06	18.57	51.04	58.89	40.74	60	67.5	50	27.67	8	40.5	44	41	25.7	16.8	48.79	44.01	21.07	36.43
TDT 2023.05		0.71	0.44	3.88	0.55	6.16	6.43	19.87	40.55	14.26	10.16	21.65	41.93	55.76	27.82	47.15	6.89	11.86	15.1	15.7	5.25	30	8.43	8.34	3.86	8	2.53	14.66	9.12	1.51	1.29	28.37	10.36	6.11	14.66
KGA2C 2023.05		0	0	4	0	6	11	4	7	4	4	4	18	44	16	15	6	11	17	19	4	43	32	23	5	10	4	4	4	11	11	22.7	6.88	4.92	11.37
CALM 2023.05		0	0	0	0	1	1	1	5	7	2	2	10	54	10	8	2	4	3	6	3	6	10	4	4	0	0	3	2	2	2	11.3	2.88	1.33	5.07