RT-QA - One-Hop (L2): leaderboard

RT-QA (2026) asks real-time questions in Chinese whose answers come from executing a verified scraping workflow at the moment of inference; models run as search agents with web search and page reading on six days in January 2026, judged by GPT-5.2. This board covers questions that first resolve the target entity in one hop. Accuracy in percent; higher is better.

Metric: Accuracy (%) on 1-hop questions that first resolve the target entity, mean of the 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 November 2027. 8 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Seed 1.845.6#252
2GLM-4.741.9#380
3RT-QA Claude-4.5 (checkpoint unspecified)39.2
4GPT-5.238#185
5RT-QA Kimi-K2 (checkpoint unspecified)37.4
6DeepSeek V3.234#419
7Gemini 3 Pro33.2#145
8RT-QA Qwen3-235B (checkpoint unspecified)26.9

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=rt-qa-one-hop-l2 · How It Works · Data refreshed daily, snapshot 2026-11-21.