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

#ModelScoreOverall rank
1Gemini 3 Pro69.8#145
2Qwen 3.5 397B A17B64.7#264
3GPT-5.262.1#185
4Qwen 3 VL 235B A22B60.3#485
5Qwen 3.5 35B A3B56.9#492
6BU-30B56.9
7Qwen 3 VL 30B A3B56#784
8Claude Sonnet 4.551.7#261
9Kimi K2.544.8#266
10GLM-4.6V0#710
11uitars-1.5-7B0#7905
12InternVL3.5-38B0#1021
13ShowUI-2B0
14GUI-G1-3B0
15UI-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.