CorpusQA (1M) - Real Estate: leaderboard
Real-estate domain of CorpusQA (Lu et al., Tongyi Lab, 2026) at the 1M-token scale (concatenated corpora of about 905K tokens, run only on models that accept million-token input): 81 analytical questions (filters, rankings, counts and computed values) answered over the whole concatenated corpus of English real-estate documents, with reference answers computed by SQL over fields extracted from every document. Accuracy in percent as judged by DeepSeek-V3 against the reference; higher is better.
Metric: Accuracy (%; 81 questions over English real-estate documents, 1M-token corpora, DeepSeek-V3 judge). Source: arxiv.org. Saturation forecast: Estimated already saturated. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 38.27 | #262 |
| 2 | Gemini 2.5 Flash | 30.86 | #452 |
| 3 | MiniMax M1 80k | 17.5 | #926 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=corpusqa-1m-real-estate · How It Works · Data refreshed daily, snapshot 2026-11-12.