INS-ActBench - R Code: leaderboard

Metric: Numerical accuracy (%; outputs of the generated R code within 0.2 percent relative tolerance) on the 516 R-code 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 August 2027. 9 models tracked.

Top models

#ModelScore
1Claude Opus 4.7 (High)71.3
2GPT-5.5 (High)71.1
3Qwen 3.6 Plus69.8
4DeepSeek V4 Pro (High)69.6
5Gemini 3.1 Pro (Preview)69
6Kimi K2.669
7Qwen 3.5 35B A3B64
8Qwen 3 14B54.8
9Gemma 3 12B (IT)44.4

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