BI-Bench (Python): leaderboard
Metric: Accuracy (%; 100 end-to-end business-intelligence queries curated from real Power BI dashboards (82 projects, raw source tables needing search, reshaping, joins and analysis); an answer is correct when the output table matches the ground-truth table in shape and cell values up to row and column order, with numeric tolerance; mean over 10 runs; Python setting: tables given as CSV files and the model iterates with a generic code-execution tool only). Source: arxiv.org. Saturation forecast: Around December 2026. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 59.5 |
| 2 | O4 Mini | 57.4 |
| 3 | Kimi K2.6 | 55.6 |
| 4 | DeepSeek V4 Pro | 53.2 |
| 5 | GPT-5.2 | 48.6 |
| 6 | Mistral Large 3 | 35 |
| 7 | GPT-4o | 30.8 |
| 8 | Llama 4 Maverick | 28.6 |
| 9 | Qwen 3 8B | 5.4 |
| 10 | GPT-OSS-120B | 3.1 |
Interactive version: theaggregate.ai/benchmark?slug=bi-bench-python · How It Works · Data refreshed daily, snapshot 2026-09-26.