FIRE (Finance, Business Scenarios) - Insurance: leaderboard
Metric: Score (%) on the insurance questions of FIRE's 3,000 business-scenario questions mapped to a sector by business-competency matrix; closed-form decision questions scored by exact match of a JSON answer, open-ended questions scored against per-question expert-refined 1-5 rubrics by the authors' scoring model (a fine-tuned Qwen3-32B); higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 14 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Seed-OSS-36B-Instruct | 82.79 | #348 |
| 2 | GPT-5.2 | 82.53 | #105 |
| 3 | Gemini 3 Pro | 79.82 | #77 |
| 4 | Seed-1.6 | 79.64 | #257 |
| 5 | DeepSeek V3.2 | 77.86 | #198 |
| 6 | GLM-4.6 | 77.11 | #246 |
| 7 | Qwen 3 Max | 76.91 | #201 |
| 8 | GPT-OSS-120B | 76.81 | #330 |
| 9 | Qwen 3 235B A22B 2507 (Thinking) | 76.45 | #253 (Qwen 3 235B A22B 2507) |
| 10 | Kimi K2 (Thinking) | 74.85 | #236 (Kimi K2) |
| 11 | Claude Sonnet 4.5 | 73.42 | #138 |
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-business-scenarios-insurance · How It Works · Data refreshed daily, snapshot 2026-10-11.