INS-ActBench - Spreadsheet: leaderboard
Metric: Numerical accuracy (%; answer cells of the generated workbook within 0.2 percent relative tolerance) on the 636 spreadsheet tasks; 12,050 questions from the exams of 16 actuarial associations; knowledge and case questions two-shot, practice tasks zero-shot; proprietary models with thinking enabled at high where supported. Source: arxiv.org. Saturation forecast: Around December 2026. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 (High) | 67.7 |
| 2 | Gemini 3.1 Pro (Preview) | 67 |
| 3 | Claude Opus 4.7 (High) | 60.6 |
| 4 | DeepSeek V4 Pro (High) | 55.2 |
| 5 | Qwen 3.6 Plus | 47.4 |
| 6 | Kimi K2.6 | 29.5 |
| 7 | Qwen 3.5 35B A3B | 16.3 |
| 8 | Qwen 3 14B | 2.7 |
| 9 | Gemma 3 12B (IT) | 1 |
Interactive version: theaggregate.ai/benchmark?slug=ins-actbench-spreadsheet · How It Works · Data refreshed daily, snapshot 2026-09-29.