FIRE (Finance, Business Scenarios) - Banking: leaderboard
Metric: Score (%) on the banking 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 | GPT-5.2 | 77.41 | #105 |
| 2 | Seed-1.6 | 75.49 | #257 |
| 3 | DeepSeek V3.2 | 74.87 | #198 |
| 4 | Seed-OSS-36B-Instruct | 74.78 | #348 |
| 5 | Gemini 3 Pro | 73.58 | #77 |
| 6 | Kimi K2 (Thinking) | 72.57 | #236 (Kimi K2) |
| 7 | Qwen 3 235B A22B 2507 (Thinking) | 72.39 | #253 (Qwen 3 235B A22B 2507) |
| 8 | GLM-4.6 | 72.1 | #246 |
| 9 | Qwen 3 Max | 71.43 | #201 |
| 10 | Claude Sonnet 4.5 | 71.33 | #138 |
| 11 | GPT-OSS-120B | 70.12 | #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-business-scenarios-banking · How It Works · Data refreshed daily, snapshot 2026-10-11.