RiskWebWorld - Payment Channel Validation: leaderboard
Metric: Task success rate (%) over the 174 secure payment channel validation 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 January 2027. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro | 39.1 |
| 2 | Qwen 3.5 35B A3B | 36.8 |
| 3 | Qwen 3 VL 235B A22B | 36.8 |
| 4 | Qwen 3.5 397B A17B | 34.5 |
| 5 | GPT-5.2 | 32.2 |
| 6 | Claude Sonnet 4.5 | 23 |
| 7 | GLM-4.6V | 13.8 |
| 8 | Kimi K2.5 | 0 |
| 9 | uitars-1.5-7B | 0 |
Interactive version: theaggregate.ai/benchmark?slug=riskwebworld-payment-channel-validation · How It Works · Data refreshed daily, snapshot 2026-10-07.