VisualWebArena: leaderboard
VisualWebArena: Measures browser, desktop, mobile, or GUI agents operating in interactive environments.
Metric: Success Rate (%). Source: jykoh.com. Saturation forecast: Estimated already saturated. 32 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Flash | 54 | #245 |
| 2 | GPT-5 | 52.9 | #98 |
| 3 | GLM-4 32B | 48.7 | #459 |
| 4 | GPT-4o | 19.78 | #343 |
| 5 | Gemini 1.5 Pro | 11.98 | #445 |
| 6 | GPT-4 | 7.25 | #438 |
| 7 | Gemini 1.5 Flash | 6.59 | #618 |
| 8 | Gemini 1.0 Pro | 6.04 | #933 |
| 9 | GPT-3.5 | 2.2 | #818 |
| 10 | Mixtral 8x7B | 1.76 | #1143 |
| 11 | Llama 2 70B | 1.1 | #1201 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=visualwebarena · How It Works · Data refreshed daily, snapshot 2026-10-20.