SpreadsheetBench v2 - Financial Modeling Accuracy: leaderboard

SpreadsheetBench v2 evaluates agents completing spreadsheet workflows on real business files. This series reports task accuracy for the financial modeling 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
1arito67
2WPS AI56
3Decide Agent 2.036
4Claude Opus 4.634#114
5GPT-5.233#185
6Gemini 3.1 Pro (Preview)31#99
7GLM-522#267
8Kimi K2.515#263
9Qwen 3.5 397B A17B10#255
10MiniMax-M2.58#589
11DeepSeek V3.27#417

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-financial-modeling-accuracy · How It Works · Data refreshed daily, snapshot 2026-11-17.