FIRE (Finance, Business Scenarios): leaderboard
Metric: Score (%) over all sectors, weighted by question count, on 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: Estimated already saturated. 14 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.2 | 77.46 | #105 |
| 2 | Seed-1.6 | 77.15 | #257 |
| 3 | Seed-OSS-36B-Instruct | 76.34 | #348 |
| 4 | Gemini 3 Pro | 75.72 | #77 |
| 5 | DeepSeek V3.2 | 75.65 | #198 |
| 6 | Qwen 3 235B A22B 2507 (Thinking) | 74.35 | #253 (Qwen 3 235B A22B 2507) |
| 7 | Kimi K2 (Thinking) | 74.19 | #236 (Kimi K2) |
| 8 | GLM-4.6 | 73.91 | #246 |
| 9 | Qwen 3 Max | 73.52 | #201 |
| 10 | GPT-OSS-120B | 71.95 | #330 |
| 11 | Claude Sonnet 4.5 | 70.22 | #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 · How It Works · Data refreshed daily, snapshot 2026-10-11.