CompliBench - Insurance - Guideline Accuracy: leaderboard
Metric: Strict guideline accuracy (%): share of compliant assistant turns in the insurance domain for which the judge predicts the correct governing guideline and no violation, of an LLM judge on CompliBench's synthesized multi-turn dialogues with injected, adversarially optimized guideline violations, mean of four runs at default reasoning effort; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 91.91 |
| 2 | Gemini 3 Pro | 91.68 |
| 3 | Qwen 3.5 Plus | 90.8 |
| 4 | Qwen 3 Max | 89.82 |
| 5 | Claude Sonnet 4.6 | 85.71 |
| 6 | DeepSeek V3.2 (Thinking) | 85.5 |
| 7 | GLM-5 | 84.62 |
| 8 | Qwen 3 30B A3B | 82.87 |
| 9 | GPT-4o | 82.7 |
| 10 | Kimi K2.5 | 78.67 |
| 11 | Qwen 3 32B | 65.05 |
| 12 | GPT-4o Mini | 56.76 |
| 13 | Qwen 3 4B | 51.01 |
| 14 | Qwen 3 8B | 48.63 |
| 15 | Qwen 3 14B | 41.97 |
Interactive version: theaggregate.ai/benchmark?slug=complibench-insurance-guideline-accuracy · How It Works · Data refreshed daily, snapshot 2026-10-07.