WTM-Bench (Python) - Charts: leaderboard

Metric: Soft score (%; partial-credit similarity to the target workbook on the level-3 tasks whose primary artifact is charts; the model drives Excel through Python with openpyxl; 150 WTM-Bench tasks at query level 3 (concise, abstract requests); the authors' tool-calling loop that executes code against the workbook, shows the resulting workbook state and allows up to 10 turns; deterministic programmatic grading). Source: arxiv.org. Saturation forecast: Around September 2028. 6 models tracked.

Top models

#ModelScore
1GPT-5.461
2Claude Opus 4.657
3GPT-5.255
4GPT-4.1 Mini52
5Claude Haiku 4.551
6Claude Sonnet 4.550

Interactive version: theaggregate.ai/benchmark?slug=wtm-bench-python-charts · How It Works · Data refreshed daily, snapshot 2026-09-29.