Exploratory Data Analysis (EDA) in Python
Complete EDA workflow: load data, check quality, compute correlations, detect outliers, and visualize distributions — all with an AI data analyst.
Open analysis →AI Data Analysis Benchmarks for Data Analysis
We defined practical analysis workflows from multiple domains, then ran them with AI Data Analyst using different LLM engines. On this page you can browse each workflow, open full notebook conversations, and compare model quality in shared score tables. The overall results show that modern LLMs perform very well on structured data analysis tasks.
Data Analysis Workflow Examples
Browse reproducible AI data analysis workflows in Data Analysis. Open any example to review prompts, conversation steps, generated code, outputs, and model-level quality scores.
How to Analyze a CSV File in Python
A step-by-step AI data analyst session: load a CSV, inspect structure, handle missing values, and generate a full exploratory summary.
Open analysis →Iris Feature Analysis and Visualization in Python
Load the Iris dataset from scikit-learn, create a seaborn feature pairplot, and explore species separation patterns using an AI data analyst.
Open analysis →Model Comparison for Data Analysis
Compare LLM performance across workflows in this category. Open any score chip to jump directly to that model run and inspect the full conversation and notebook output.
Average score (0-10)
glm-5.1
10.00
n=3
gpt-oss:120b
10.00
n=3
gpt-5.4
9.67
n=3
gemma4:31b
9.33
n=3
qwen3-coder-next
9.33
n=3
qwen3.5:397b
8.00
n=3
glm-5.1
Average score: 10.00/10
Scored workflows: 3
gpt-oss:120b
Average score: 10.00/10
Scored workflows: 3
gpt-5.4
Average score: 9.67/10
Scored workflows: 3
gemma4:31b
Average score: 9.33/10
Scored workflows: 3
qwen3-coder-next
Average score: 9.33/10
Scored workflows: 3
qwen3.5:397b
Average score: 8.00/10
Scored workflows: 3
Detailed Workflow Comparison Table for Data Analysis
This table compares model scores for each workflow in Data Analysis. Open any score chip to jump directly to the selected model conversation and review full prompts, code, outputs, and score cards.
| Workflow | gemma4:31b | glm-5.1 | gpt-5.4 | gpt-oss:120b | qwen3-coder-next | qwen3.5:397b |
|---|---|---|---|---|---|---|
| Exploratory Data Analysis (EDA) in Python exploratory-data-analysis-python | 8.0/10 | 10.0/10 | 10.0/10 | 10.0/10 | 10.0/10 | 10.0/10 |
| How to Analyze a CSV File in Python analyze-csv-python | 10.0/10 | 10.0/10 | 9.0/10 | 10.0/10 | 9.0/10 | 4.0/10 |
| Iris Feature Analysis and Visualization in Python iris-feature-analysis | 10.0/10 | 10.0/10 | 10.0/10 | 10.0/10 | 9.0/10 | 10.0/10 |
What This Benchmark Shows
We tested the same step-by-step data analysis workflows across multiple LLM models and compared results using a shared scoring rubric. In Data Analysis, most models produce strong notebook outputs with high task completion and useful analytical reasoning. Use these examples as a reference for prompt design, model selection, and workflow quality before running similar analyses on your own data in MLJAR Studio.
Start using AI for Data Analysis
MLJAR Studio helps you analyze data with AI, run machine learning workflows, and build reproducible notebook-based results on your own computer.
Runs locally • Supports local LLMs