FinRiskAtlas - Applied Review - Applicable-Provision Selection: leaderboard
FinRiskAtlas fixed-evidence review operation: selecting the governing provisions from a candidate set, scored by a set-based accuracy-style measure (FinRiskAtlas, arXiv 2608.25325v1, Appendix Table 9). Percent; higher is better. Reported for 33 archived model configurations under zero-shot direct-answer inference.
Metric: Set-Based Accuracy (%). Source: arxiv.org. Saturation forecast: Around February 2027. 33 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Sol | 67.55 | #22 |
| 2 | Gemini 2.5 Flash | 66.25 | #255 |
| 3 | Gemini 3 Flash (Preview) | 65.75 | #90 |
| 4 | GPT-5.4 | 60.45 | #83 |
| 5 | GPT-5.6 Terra | 56.95 | #40 |
| 6 | Seed 2.0 Lite | 56.4 | #161 |
| 7 | GPT-5.4 Mini | 55.35 | #228 |
| 8 | Claude Opus 4.7 | 54.8 | #51 |
| 9 | DeepSeek V4 Flash | 53 | #155 |
| 10 | Ling-2.6-1T | 52.1 | #307 |
| 11 | Kimi K3 | 51.65 | #35 |
| 12 | GLM-5 | 51.5 | #149 |
| 13 | GLM-5.2 | 51.15 | #80 |
| 14 | GPT-5.6 Luna | 50.8 | #79 |
| 15 | Qwen 3.7 Max | 46.85 | #85 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=finriskatlas-applied-review-applicable-provision-selection · How It Works · Data refreshed daily, snapshot 2026-11-05.