FinRiskAtlas - Domain Knowledge - FinTech & Security: leaderboard
Macro-averaged accuracy on the FinTech & Security group of FinRiskAtlas domain-knowledge task families, a subset of the 42-family knowledge layer used for coarse screening of financial-review models (FinRiskAtlas, arXiv 2608.25325v1, Appendix Table 8). Percent; higher is better; zero-shot direct answers from 33 archived configurations.
Metric: Macro-Averaged Accuracy (%). Source: arxiv.org. Saturation forecast: Around February 2027. 33 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.7 | 86.92 | #51 |
| 2 | Qwen 3.7 Max | 85.04 | #85 |
| 3 | GPT-5.4 | 84.69 | #83 |
| 4 | Gemini 3 Flash (Preview) | 84.33 | #90 |
| 5 | Kimi K3 | 84.07 | #35 |
| 6 | Ling-2.6-1T | 83.22 | #307 |
| 7 | Qwen 3 235B A22B | 83.02 | #323 |
| 8 | DeepSeek V4 Pro | 82.73 | #112 |
| 9 | Qwen3-Next-80B | 82.52 | #321 |
| 10 | Kimi K2.5 | 82.15 | #152 |
| 11 | GPT-5.6 Terra | 81.19 | #40 |
| 12 | GPT-5.4 Mini | 80.59 | #228 |
| 13 | Gemini 2.5 Flash | 80.56 | #255 |
| 14 | Seed 2.0 Mini | 80.43 | #279 |
| 15 | GLM-5.2 | 80.33 | #80 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=finriskatlas-domain-knowledge-fintech-security · How It Works · Data refreshed daily, snapshot 2026-11-05.