EvoGUI-Bench - Temporal Ordering: leaderboard
The temporal ordering probe of EvoGUI-Bench (Tsinghua University, 2026): put 3 to 5 shuffled screenshots from one web session back in chronological order. Exact-match accuracy in percent; higher is better.
Metric: Exact ordering accuracy (%; share of 1,000 sets of 3 to 5 shuffled screenshots from one session put back in chronological order; 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 April 2027. 28 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Flash (Preview) | 58.3 | #144 |
| 2 | Doubao-Seed-2.0-Pro-260215 | 44.4 | #152 |
| 3 | GPT-5.4 | 42.1 | #123 |
| 4 | Qwen 3.5 397B A17B | 34.4 | #246 |
| 5 | Kimi K2.6 | 34.4 | #178 |
| 6 | MiMo-V2.5 | 34.2 | #354 |
| 7 | Kimi K2.5 | 33.4 | #256 |
| 8 | Qwen 3.6 35B A3B | 33.3 | #462 |
| 9 | Qwen 3.5 122B A10B | 32.8 | #331 |
| 10 | GLM-5V Turbo | 31.9 | #344 |
| 11 | Qwen 3.5 35B A3B | 31.1 | #482 |
| 12 | Qwen 3 VL 235B A22B Instruct | 30.9 | #522 |
| 13 | GLM-4.5V | 30.9 | #744 |
| 14 | GPT-5 Mini | 30.3 | #348 |
| 15 | Qwen 3.5 27B | 29.7 | #359 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=evogui-bench-temporal-ordering · How It Works · Data refreshed daily, snapshot 2026-11-13.