INS-ActBench - Actuarial Mathematics: leaderboard

Metric: Accuracy (%) on the 1,134 actuarial mathematics knowledge questions; 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

#ModelScore
1Gemini 3.1 Pro (Preview)94.8
2GPT-5.5 (High)93.1
3DeepSeek V4 Pro (High)92.2
4Qwen 3.6 Plus89.9
5Claude Opus 4.7 (High)76.6
6Kimi K2.664.7
7Qwen 3 14B38.2
8Qwen 3.5 35B A3B33.8
9Gemma 3 12B (IT)32.2

Interactive version: theaggregate.ai/benchmark?slug=ins-actbench-actuarial-mathematics · How It Works · Data refreshed daily, snapshot 2026-09-29.