RiskWebWorld - Customs Clearance Audit: leaderboard
RiskWebWorld (2026) gives web GUI agents e-commerce risk-management tasks from a production risk-control pipeline, run on real, often uncooperative websites within 20 steps. Task success rate over the 116 customs declaration and clearance status audit tasks, in percent; higher is better.
Metric: Task success rate (%) over the 116 customs declaration and clearance status audit tasks, for web GUI agents in RiskWebWorld's Browser Use style loop (DOM tree, screenshot and history each step, 1920x1080 viewport, at most 20 steps, stopped after three consecutive failed actions), default model settings; exact match for exact fields, an LLM judge for free-text fields; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 15 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro | 69.8 | #145 |
| 2 | Qwen 3.5 397B A17B | 64.7 | #264 |
| 3 | GPT-5.2 | 62.1 | #185 |
| 4 | Qwen 3 VL 235B A22B | 60.3 | #485 |
| 5 | Qwen 3.5 35B A3B | 56.9 | #492 |
| 6 | BU-30B | 56.9 | |
| 7 | Qwen 3 VL 30B A3B | 56 | #784 |
| 8 | Claude Sonnet 4.5 | 51.7 | #261 |
| 9 | Kimi K2.5 | 44.8 | #266 |
| 10 | GLM-4.6V | 0 | #710 |
| 11 | uitars-1.5-7B | 0 | #7905 |
| 12 | InternVL3.5-38B | 0 | #1021 |
| 13 | ShowUI-2B | 0 | |
| 14 | GUI-G1-3B | 0 | |
| 15 | UI-TARS-72B (RiskWebWorld checkpoint unspecified) | 0 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=riskwebworld-customs-clearance-audit · How It Works · Data refreshed daily, snapshot 2026-11-21.