WTM-Bench (Office.js) - Soft Score: leaderboard

Metric: Soft score (%; weighted component similarity of cells, formulas, charts, pivot tables and conditional formatting to the target workbook, partial credit; the model drives Excel through Office.js; 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 February 2028. 6 models tracked.

Top models

#ModelScore
1Claude Opus 4.648.1
2Claude Sonnet 4.546.1
3GPT-5.244.3
4GPT-5.440.9
5Claude Haiku 4.536.7
6GPT-4.1 Mini29.3

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