INS-ActBench - Case Analysis: 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 is the exact-set accuracy on the 1,149 multiple-answer case questions over contexts of up to 175K tokens, in percent; higher is better.
Metric: Exact-set accuracy (%) on the 1,149 long-context multiple-answer case questions (INS-Act-Case, contexts up to 175K tokens); 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 | GPT-5.5 (High) | 56.3 | #49 (GPT-5.5) |
| 2 | Gemini 3.1 Pro (Preview) | 55.5 | #94 |
| 3 | Qwen 3.6 Plus | 44.6 | #222 |
| 4 | DeepSeek V4 Pro (High) | 43.9 | #188 (DeepSeek V4 Pro) |
| 5 | Claude Opus 4.7 (High) | 43.3 | #79 (Claude Opus 4.7) |
| 6 | Kimi K2.6 | 24.8 | #178 |
| 7 | Qwen 3.5 35B A3B | 20.2 | #482 |
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-case-analysis · How It Works · Data refreshed daily, snapshot 2026-11-13.