RiskWebWorld - Logistics Tracking: 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 166 logistics and supply chain tracking tasks, in percent; higher is better.

Metric: Task success rate (%) over the 166 logistics and supply chain tracking 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 Pro56.6#146
2Kimi K2.550#272
3GPT-5.248.8#190
4Qwen 3.5 397B A17B43.4#270
5Qwen 3 VL 235B A22B42.7#486
6Claude Sonnet 4.530.1#267
7Qwen 3.5 35B A3B25.3#494
8BU-30B19.3
9Qwen 3 VL 30B A3B18.7#791
10GLM-4.6V0#721
11uitars-1.5-7B0#7957
12InternVL3.5-38B0#1026
13ShowUI-2B0
14GUI-G1-3B0
15UI-TARS-72B (RiskWebWorld checkpoint unspecified)0

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=riskwebworld-logistics-tracking · How It Works · Data refreshed daily, snapshot 2026-11-22.