INS-ActBench: leaderboard
Metric: Accuracy (%; unweighted mean of the knowledge, case and practice subset totals) on 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
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 (High) | 72.9 |
| 2 | Gemini 3.1 Pro (Preview) | 72.7 |
| 3 | DeepSeek V4 Pro (High) | 65.6 |
| 4 | Qwen 3.6 Plus | 63.3 |
| 5 | Claude Opus 4.7 (High) | 63.3 |
| 6 | Kimi K2.6 | 47.6 |
| 7 | Qwen 3.5 35B A3B | 32 |
| 8 | Qwen 3 14B | 29.1 |
| 9 | Gemma 3 12B (IT) | 24 |
Interactive version: theaggregate.ai/benchmark?slug=ins-actbench · How It Works · Data refreshed daily, snapshot 2026-09-29.