FIRE (Finance, Business Scenarios) - Trust: leaderboard
Metric: Score (%) on the trust 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: Around January 2027. 14 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.2 | 75 | #105 |
| 2 | Gemini 3 Pro | 72.06 | #77 |
| 3 | Qwen 3 Max | 71.21 | #201 |
| 4 | Seed-OSS-36B-Instruct | 70 | #348 |
| 5 | GLM-4.6 | 66.18 | #246 |
| 6 | Qwen 3 235B A22B 2507 (Thinking) | 66.17 | #253 (Qwen 3 235B A22B 2507) |
| 7 | Seed-1.6 | 65.44 | #257 |
| 8 | DeepSeek V3.2 | 63.97 | #198 |
| 9 | Kimi K2 (Thinking) | 63.97 | #236 (Kimi K2) |
| 10 | GPT-OSS-120B | 57.35 | #330 |
| 11 | Claude Sonnet 4.5 | 50.74 | #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-trust · How It Works · Data refreshed daily, snapshot 2026-10-11.