WTM-Bench (Office.js): leaderboard
WTM-Bench (2026) gives a model a public Excel workbook with its derived artifacts removed and a concise level-3 request, and asks it to recreate the formulas, charts, pivot tables or conditional formatting by writing code in a tool loop of up to 10 turns; outputs are graded programmatically against the original workbook. Here the model drives Excel through Office.js. Score is the hard score, the share of tasks reproduced exactly, in percent; higher is better.
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 June 2028. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.5 | 22 | #250 |
| 2 | Claude Opus 4.6 | 19.3 | #102 |
| 3 | GPT-5.4 | 14.7 | #123 |
| 4 | GPT-5.2 | 14.4 | #176 |
| 5 | Claude Haiku 4.5 | 12 | #568 |
| 6 | GPT-4.1 Mini | 9.3 | #779 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=wtm-bench-office-js · How It Works · Data refreshed daily, snapshot 2026-11-13.