List your company

Interactive Science Simulation on ScienceWorld v1.0 (test)

97.04Task 1-1 (L) ScoreSwiftSage
-3.881622.319248.5274.7208May 27, 2023

Evaluation results

MethodLinks
SwiftSageBase LLM=GPT-42023.0597.0487.0472.7810099.1788.1795.7388.6755.3371.977.8610010091.6710074.5993.9349.410091.48958593.338968.575706092.377.692.2277.798384.68
SayCanBase LLM=GPT-42023.0533.0610.393.880.3726.378.0317.4152.1422.599.5647.7622.8758.1820.8731.439.9213.9347.8139.2619.728067.55020.911621.9432.2613.6767.5359.4543.8336.5823.6533.82
ReflexionBase LLM=GPT-42023.054.2210.617.780.925.9228.5922.3710017.4572.5470.2264.9387.2716.421007.331370.3570.6715.7710084.37832.58850.6310070.6250.923.6971.4735.4330.1745.34
DRRN2023.053.523.52006.565.561299.059.52154521.6719.17814.2915.7726.6710.37505033.3321810101016.81728.0810.858.2615.56
ReActBase LLM=GPT-42023.053.5213.77.789.887.196.122.375654.3376.1988.8126.678053.3327.59.0618.5751.0458.8940.746067.55027.67840.5444125.716.848.7944.0121.0736.43
TDT2023.050.710.443.880.556.166.4319.8740.5514.2610.1621.6541.9355.7627.8247.156.8911.8615.115.75.25308.438.343.8682.5314.669.121.511.2928.3710.366.1114.66
KGA2C2023.050040611474441844161561117194433223510444111122.76.884.9211.37
CALM2023.05000011157221054108243636104400322211.32.881.335.07