Assessment of Gaussian-2 and density functional theories for the computation of enthalpies of formation

A set of 148 molecules having well-established enthalpies of formation at 248 K is presented. This set, referred to as the G2 neutral test set, includes the 55 molecules whose atomization energies were used to test Gaussian-2 (G2) theory [J. Chem. Phys. 94, 7221 (1991)] and 93 new molecules. The G2 test set includes 29 radicals, 35 nonhydrogen systems, 22 hydrocarbons, 47 substituted hydrocarbons, and 15 inorganic hydrides. It is hoped that this new test set will provide a means for assessing and improving new theoretical models. From an assessment of G2 and density functional theories (DFT) on this test set it is found that G2 theory is the most reliable method both in terms of average absolute deviation (1.58 kcal/mol) and maximum; deviation (8.2 kcal/mol). The largest deviations between experiment and G2 theory occur for molecules having multiple halogens. Inclusion of spin-orbit effects reduces the average absolute deviation to 1.47 kcal/mol and significantly improves the results for the chlorine substituted molecules, but little overall improvement is seen for the fluorine substituted molecules. Of the two modified versions of G2 theory examined in this study, G2(MP2,SVP) theory (average absolute deviation = 1.93 kcal/mol) performs better than G2(MP2) theory (2.04 kcal/mol). The G2(MP2,SVP) theory is found to perform very well for hydrocarbons, radicals, and inorganic hydrides. Of the seven DFT methods investigated, the B3LYP method has the smallest average absolute deviation (3.11 kcal/mol). It also has a significantly larger distribution of error than the G2 methods with a maximum deviation of 20.1 kcal/mol. (C) 1997 American Institute of Physics.