WTM-Bench (Office.js): leaderboard

Metric: Hard score (%; share of tasks whose output workbook matches the target exactly, a perfect soft score; 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 2029. 6 models tracked.

Top models

#ModelScore
1Claude Sonnet 4.522
2Claude Opus 4.619.3
3GPT-5.414.7
4GPT-5.214.4
5Claude Haiku 4.512
6GPT-4.1 Mini9.3

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