SpreadsheetBench v2 - Template Accuracy: leaderboard

SpreadsheetBench v2 evaluates agents completing spreadsheet workflows on real business files. This series reports task accuracy for the template category from the official leaderboard, preserving its named agent products and SWE-agent model runs. Accuracy is the percentage of tasks solved, distinct from the paper's cell-match metric. Higher is better.

Metric: Task accuracy (%). Source: spreadsheetbench.github.io. Saturation forecast: Around February 2027. 11 models tracked. Updated 2 Oct 2026.

Top models

#ModelScoreOverall rank
1WPS AI76.29
2arito62.89
3Decide Agent 2.062.89
4Claude Opus 4.652.58#114
5GPT-5.235.05#185
6Gemini 3.1 Pro (Preview)28.87#99
7DeepSeek V3.225.77#417
8Kimi K2.518.56#263
9Qwen 3.5 397B A17B17.53#255
10GLM-517.53#267
11MiniMax-M2.57.22#589

No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.

Interactive version: theaggregate.ai/benchmark?slug=spreadsheetbench-v2-template-accuracy · How It Works · Data refreshed daily, snapshot 2026-11-17.