EvoGUI-Bench: leaderboard
Metric: EvoGain index (mean over the three probes of the gain over the random baseline normalized by the headroom above it, times 100: temporal ordering exact-match accuracy, inverse action and value joint accuracy and one-step successor accuracy; 100 is perfect, 0 is random and below-random performance is negative, down to about -42; on EvoGUI-Bench, 3,000 zero-shot visual question answering probes mined from Mind2Web and WebLINX web trajectories across 120 domains, screenshots at max_image_side 512, temperature 0; higher is better). Source: arxiv.org. Saturation forecast: Around 2029. 28 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 60.4 |
| 2 | Doubao-Seed-2.0-Pro-260215 | 49.8 |
| 3 | Kimi K2.6 | 43.9 |
| 4 | Qwen 3.5 122B A10B | 43.8 |
| 5 | GPT-5.4 | 43.4 |
| 6 | MiMo-V2.5 | 42.4 |
| 7 | Qwen 3.6 35B A3B | 42 |
| 8 | GLM-5V Turbo | 41.9 |
| 9 | Kimi K2.5 | 41.6 |
| 10 | Qwen 3.5 35B A3B | 40.5 |
| 11 | Qwen 3.5 27B | 39.6 |
| 12 | Qwen 3.5 397B A17B | 39.5 |
| 13 | Qwen 3.6 27B | 38.5 |
| 14 | Qwen 3 VL 235B A22B | 37.5 |
| 15 | GLM-4.5V | 37.1 |
Interactive version: theaggregate.ai/benchmark?slug=evogui-bench · How It Works · Data refreshed daily, snapshot 2026-09-29.