Machining　accuracy　reliability　is　considered　to　be　one　of　the　most　important　indexes　in　the　process　of　performance　evaluation　and　optimization　design　of　the　machine　tools.　Geometric　errors,　thermal　errors　and　tool　wear　are　the　main　factors　to　affect　the　machining　accuracy　and　so　affect　the　machining　accuracy　reliability　of　machine　tools.　This　paper　proposed　a　geometric　error　budget　method　that　simultaneously　considers　geometric　errors,　thermal　errors　and　tool　wear　to　improve　the　machining　accuracy　reliability　of　machine　tools.　Homogeneous　transformation　matrices,　neural　fuzzy　control　theory　and　a　tool　wear　predictive　approach　were　employed　to　develop　a　comprehensive　error　model,　which　shows　the　influence　of　the　geometric,　thermal　errors　and　tool　wear　to　the　machining　accuracy　of　a　machine　tool.　Based　on　Rackwite-Fiessler　and　Advanced　First　Order　and　Second　Moment,　a　reliability　model　and　a　sensitivity　model　were　put　forward,　which　can　deal　with　the　errors　of　a　machine　tool　drawn　from　any　distribution.　Then,　a　geometric　error　budget　method　of　multi-axis　NC　machine　tool　was　developed　and　formed　into　a　mathematical　model.　In　such　method,　the　minimum　cost　of　machine　tool　was　the　optimization　objective,　the　reliability　of　the　machining　accuracy　was　the　constraint,　and　the　sensitivity　was　to　identify　the　geometric　errors　to　be　optimized.　An　example　conducted　on　a　five-axis　NC　machine　tool　was　used　to　explain　and　validate　the　proposed　method.