Large Language Models (LLMs) exhibit impressive linguistic fluency, yet it remains unclear whether they possess human-like Theory of Mind (ToM) or merely rely on statistical heuristics, particularly in complex social tasks such as irony comprehension. To address the limitations of existing binary benchmarks, this study establishes a multi-dimensional evaluation framework comprising 140 carefully designed probes. These probes are derived from 10 story prototypes based on established cognitive theories. The framework systematically modulates contextual contrast, linguistic cues, and cognitive mechanisms. By comparing the performance of ten state-of-the-art LLMs against 300 human participants, this study uncovers a significant dichotomy in performance. Although LLMs demonstrate superior sensitivity in subsidiary pragmatic inferences, human participants outperform them in holistic irony judgment. Crucially, the results reveal a systematic "intent-irony decoupling", wherein LLMs fail to integrate pragmatic signals into their final judgments. These models exhibit aggressive decision biases and rely on "context-utterance conflict" heuristics. These findings suggest that current LLMs simulate irony comprehension without the underlying cognitive mechanisms. The development of future artificial intelligence may require the integration of explicit ToM modules to bridge the gap between surface-level pattern matching and genuine social understanding.