# Token Signatures of Code: Comparing Coding Behaviors Across Large Language Models

arXiv: https://arxiv.org/abs/2609.22097 · HTML: https://mlsanity.com/paper/2609.22097/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 47 of its 72 references that are in the map.
- First posted on arXiv 12 Aug 2026.

## Builds on (most cited first, 30 of 47)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering](https://mlsanity.com/paper/2410.07095/) (2024)
- [Evaluating Large Language Models at Evaluating Instruction Following](https://mlsanity.com/paper/2310.07641/) (2023)
- [Revisiting Classifier Two-Sample Tests](https://mlsanity.com/paper/1610.06545/) (2016)
- [SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models](https://mlsanity.com/paper/2402.05044/) (2024)
- [The What-If Tool: Interactive Probing of Machine Learning Models](https://mlsanity.com/paper/1907.04135/) (2019)
- [RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts](https://mlsanity.com/paper/2411.15114/) (2024)
- [InFoBench: Evaluating Instruction Following Ability in Large Language Models](https://mlsanity.com/paper/2401.03601/) (2024)
- [Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers](https://mlsanity.com/paper/1801.06889/) (2018)
- [A Survey on Code Generation with LLM-based Agents](https://mlsanity.com/paper/2508.00083/) (2025)
- [ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing](https://mlsanity.com/paper/2309.09128/) (2023)
- [EvalLM: Interactive Evaluation of Large Language Model Prompts on User-Defined Criteria](https://mlsanity.com/paper/2309.13633/) (2023)
- [AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench](https://mlsanity.com/paper/2507.02554/) (2025)
- [Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models](https://mlsanity.com/paper/1804.09299/) (2018)
- [RuleMatrix: Visualizing and Understanding Classifiers with Rules](https://mlsanity.com/paper/1807.06228/) (2018)
- [Do Convolutional Neural Networks Learn Class Hierarchy?](https://mlsanity.com/paper/1710.06501/) (2017)
- [ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning](https://mlsanity.com/paper/2506.16499/) (2025)
- [MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement](https://mlsanity.com/paper/2506.15692/) (2025)
- [Towards Better Analysis of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1604.07043/) (2016)
- [VisEval: A Benchmark for Data Visualization in the Era of Large Language Models](https://mlsanity.com/paper/2407.00981/) (2024)
- [R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Science](https://mlsanity.com/paper/2505.14738/) (2025)
- [How Does Attention Work in Vision Transformers? A Visual Analytics Attempt](https://mlsanity.com/paper/2303.13731/) (2023)
- [Visualization Generation with Large Language Models: An Evaluation](https://mlsanity.com/paper/2401.11255/) (2024)

## Abstract (arXiv)

The evaluation of large language models (LLMs) on coding tasks has primarily focused on performance metrics such as pass@k. As LLMs continue to advance, many models now meet baseline performance requirements, reducing the discriminative power of performance-based evaluation alone. Yet a key question remains largely unexplored: how do LLMs differ in their coding behavior? We propose CLIC (Code Learning for Identification and Comparison), a visual analytics approach that characterizes LLM coding behavior through token-frequency analysis. CLIC represents each code sample as a feature vector of token frequencies and trains an interpretable decision tree to separate two LLMs' code sets. Beyond classification accuracy, we define two new metrics: robustness, which measures whether the two LLMs remain distinguishable as their most-discriminative tokens are progressively removed, and concentration, which measures whether the difference is driven by a few dominant tokens or spread across many. Interpreting numerous pairwise comparisons (across LLM pairs, tasks, and tokenization levels) and tracing the full analytical chain form an inherently multi-scale, hypothesis-driven exploration task. We therefore develop an interactive visual analytics system to navigate the comparison landscape, identify pairs of interest, and drill down into discriminative tokens and their code contexts. Case studies comparing 10 LLMs across 22 Kaggle ML tasks reveal actionable insights for LLM selection and prompt engineering.