INS-ActBench - R Code: leaderboard
INS-ActBench (Fudan University, 2026) builds 12,050 actuarial questions from the exams of 16 actuarial associations, split into standardized knowledge, long-context insurance case analysis and spreadsheet or R-code practice tasks. This board covers the 516 R-code tasks, where the model writes R code that computes the requested statistics, scored by numerical accuracy in percent; higher is better.
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 February 2027. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.7 (High) | 71.3 | #79 (Claude Opus 4.7) |
| 2 | GPT-5.5 (High) | 71.1 | #49 (GPT-5.5) |
| 3 | Qwen 3.6 Plus | 69.8 | #222 |
| 4 | DeepSeek V4 Pro (High) | 69.6 | #188 (DeepSeek V4 Pro) |
| 5 | Gemini 3.1 Pro (Preview) | 69 | #94 |
| 6 | Kimi K2.6 | 69 | #178 |
| 7 | Qwen 3.5 35B A3B | 64 | #482 |
| 8 | Qwen 3 14B | 54.8 | #1233 |
| 9 | Gemma 3 12B (IT) | 44.4 | #1837 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=ins-actbench-r-code · How It Works · Data refreshed daily, snapshot 2026-11-13.