Despite their vast importance to inorganic chemistry, materials science, and catalysis, the accuracy of modeling the formation or cleavage of metal-ligand (M-L) bonds depends greatly on the chosen functional and the type of bond in a way that is not systematically understood. In order to approach a state of high-accuracy DFT for rational prediction of chemistry and catalysis, such system-dependencies need to be resolved. We studied 30 different density functionals applied to a "balanced data set" of 60 experimental diatomic M-L bond energies; this data set has no bias toward any d configuration, metal, bond type, or ligand as all of these occur to the same extent, and we can therefore identify accuracy bottlenecks. We show that the performance of a functional is very dependent on data set choice, and we dissect these effects into system type. In addition to the use of balanced data sets, we also argue that the precision (rather than just accuracy) of a functional is of interest, measured by standard deviations of the errors. There are distinct system dependencies both in the ligand and metal series: Hydrides are best described by a very large HF exchange percentage, possibly due to self-interaction error, whereas halides are best described by very small (0-10%) HF exchange fractions, and double-bond enforcing oxides and sulfides favor 10-25% HF exchange, as is also average for the full data set. Thus, average HF requirements hide major system-dependent requirements. For late transition metals Co-Zn, HF percentage of 0-10% is favored, whereas for the early transition metals Sc-Fe hybrid functionals with 20% HF exchange or higher are commonly favored. Accordingly, B3LYP is an excellent choice for early d-block but a poor choice for late transition metals. We conclude that DFT intrinsically underestimates the bond strengths of late vs early transition metals, correlating with increased effective nuclear charge. Thus, the revised RPBE, which reduces the overbinding tendency of PBE, is mainly an advantage for the early and mid transition metals and not very much for the late transition metals, i.e. there is a metal-dependent effect of the relative performance of RPBE vs PBE, which are widely used to study adsorption energetics on metal surfaces. Overall, the best performing functionals are PW6B95, the MN15 and MN15-L functionals, and the double hybrid B2PLYP.

 Users may download and print one copy of any publication from the public portal for the purpose of private study or research.  You may not further distribute the material or use it for any profit-making activity or commercial gain  You may freely distribute the URL identifying the publication in the public portal If you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.

 Users may download and print one copy of any publication from the public portal for the purpose of private study or research.  You may not further distribute the material or use it for any profit-making activity or commercial gain  You may freely distribute the URL identifying the publication in the public portal If you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.

 Users may download and print one copy of any publication from the public portal for the purpose of private study or research.  You may not further distribute the material or use it for any profit-making activity or commercial gain  You may freely distribute the URL identifying the publication in the public portal If you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.

The accuracy of density functional theory (DFT) limits predictions in theoretical catalysis, and strong chemical bonds between transition metals and oxygen pose a particular challenge. We benchmarked 30 diverse density functionals against the bond dissociation enthalpies (BDE) of the 30 MO and 30 MO+ diatomic systems of all the 3d, 4d, and 5d metals, to test universality across the d‐block as required in comparative studies. Seven functionals, B98, B97‐1, B3P86, B2PLYP, TPSSh, B3LYP, and B97‐2, display mean absolute errors (MAE) <30 kJ/mol. In contrast, many commonly used functionals such as PBE and RPBE overestimate M−O bonding by +30 kJ/mol and display MAEs from 48–76 kJ/mol. RPBE and OPBE reduce the over‐binding of PBE but remain very inaccurate. We identify a linear relationship (p‐value 7.6 ⋅ 10−5) between the precision and accuracy of DFT, i. e. inaccurate functionals tend to produce larger, unpredictable random errors. Some functionals commonly deviate from this relationship: Thus, M06‐2X is very precise but not very accurate, whereas B3LYP* and MN15‐L are more accurate but less precise than M06‐2X. The best‐performing hybrids have 10–30 % HF exchange, but this can be relieved by double hybrids (B2PLYP). Most functionals describe trends well, but errors comparing 5d to 4d/3d are ∼10 kJ/mol larger than group‐wise errors, due to uncertainties in the spin‐orbit coupling corrections for effective core potentials, affecting e. g. Pt/Pd or Au/Ag comparisons.