EvoGenUI-Bench - Interaction: leaderboard
Metric: Turn pass rate (%; share of the 250 executable-interaction turns whose artifact passes every hidden requirement; 150 five-turn generative-UI tasks (750 turns) in three suites of 50: information presentation, executable interaction and tool-grounded external state; each turn's artifact is executed in a browser and a MiMo-V2.5 evaluator checks hidden requirements from screenshots, source and DOM evidence, MiMo-V2.5 actor traces and runtime logs; turns left unexecuted after an earlier build failure or invalid output count as failures; temperature 0). Source: arxiv.org. Saturation forecast: Around December 2026. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 81.2 |
| 2 | GPT-5.5 | 77.6 |
| 3 | Claude Haiku 4.5 (20251001) | 56 |
| 4 | Gemini 3 Flash (Preview) | 47.6 |
| 5 | Qwen 3.6 Plus | 46.8 |
| 6 | Gemini 3.1 Pro (Preview) | 25.2 |
| 7 | GLM 4.5 Air | 24.8 |
| 8 | Qwen 3 Coder 480B A35B Instruct | 21.2 |
Interactive version: theaggregate.ai/benchmark?slug=evogenui-bench-interaction · How It Works · Data refreshed daily, snapshot 2026-09-29.