RT-QA: leaderboard
Metric: Accuracy (%) over all questions and all six days; Chinese real-time questions whose answers come from executing a verified scraping workflow at the moment of inference, asked daily from January 10 to 15, 2026; a DeepResearch-style agent with Serper search and Jina page reading, the current timestamp in the prompt, temperature 0.6; a GPT-5.2 judge checks semantic equivalence; higher is better. Source: arxiv.org. Saturation forecast: Around April 2028. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Seed 1.8 | 46.5 |
| 2 | GLM-4.7 | 45.2 |
| 3 | GPT-5.2 | 41 |
| 4 | Gemini 3 Pro | 37.3 |
| 5 | DeepSeek V3.2 | 35.1 |
Interactive version: theaggregate.ai/benchmark?slug=rt-qa · How It Works · Data refreshed daily, snapshot 2026-10-07.