INS-ActBench - Case Analysis: leaderboard

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 April 2027. 9 models tracked.

Top models

#ModelScore
1GPT-5.5 (High)56.3
2Gemini 3.1 Pro (Preview)55.5
3Qwen 3.6 Plus44.6
4DeepSeek V4 Pro (High)43.9
5Claude Opus 4.7 (High)43.3
6Kimi K2.624.8
7Qwen 3.5 35B A3B20.2

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