FIRE (Finance, Qualification Exams) - Life Insurance (CLIQ): leaderboard
Metric: Accuracy (%) on the China Life Insurance questions of FIRE's financial-qualification set (about 14,000 multiple-choice questions from 14 professional certification exams); exact option match; each model with its recommended inference settings, else temperature 0.6 and top-p 0.8; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 14 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro | 89.4 | #77 |
| 2 | Seed-1.6 | 87.65 | #257 |
| 3 | Qwen 3 Max | 85.87 | #201 |
| 4 | DeepSeek V3.2 | 84.67 | #198 |
| 5 | Seed-OSS-36B-Instruct | 84.67 | #348 |
| 6 | Qwen 3 235B A22B 2507 (Thinking) | 84.57 | #253 (Qwen 3 235B A22B 2507) |
| 7 | GPT-5.2 | 83.95 | #105 |
| 8 | Kimi K2 (Thinking) | 82.1 | #236 (Kimi K2) |
| 9 | Claude Sonnet 4.5 | 81.38 | #138 |
| 10 | GLM-4.6 | 81.38 | #246 |
| 11 | GPT-OSS-120B | 70.78 | #330 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=fire-finance-qualification-exams-life-insurance-cliq · How It Works · Data refreshed daily, snapshot 2026-10-11.