CorpusQA (128K) - Real Estate: leaderboard
Real-estate domain of CorpusQA (Lu et al., Tongyi Lab, 2026) at the 128K-token scale (concatenated corpora of about 92K tokens): 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, 128K-token corpora, DeepSeek-V3 judge). Source: arxiv.org. Saturation forecast: Around February 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Flash | 79.01 | #452 |
| 2 | Qwen 3 235B A22B 2507 (Thinking) | 76.54 | #460 |
| 3 | Gemini 2.5 Pro | 74.07 | #262 |
| 4 | GPT-5 | 74.07 | #163 |
| 5 | GPT-5 Mini (2025-08-07) | 72.84 | #341 |
| 6 | Qwen 3 30B A3B 2507 (Thinking) | 69.14 | #759 |
| 7 | MiniMax M1 80k | 66.67 | #926 |
| 8 | DeepSeek R1 0528 | 64.2 | #425 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=corpusqa-128k-real-estate · How It Works · Data refreshed daily, snapshot 2026-11-12.