CorpusQA (128K) - Financial (Chinese): leaderboard
Metric: Accuracy (%; 83 questions over Chinese financial reports, 128K-token corpora, DeepSeek-V3 judge). Source: arxiv.org. Saturation forecast: Estimated already saturated. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 93.98 |
| 2 | GPT-5 Mini | 93.98 |
| 3 | Qwen 3 235B A22B 2507 (Thinking) | 90.36 |
| 4 | Gemini 2.5 Pro | 89.16 |
| 5 | Gemini 2.5 Flash | 83.13 |
| 6 | DeepSeek R1 0528 | 83.13 |
| 7 | Qwen 3 30B A3B 2507 (Thinking) | 83.13 |
| 8 | MiniMax M1 80k | 73.49 |
Interactive version: theaggregate.ai/benchmark?slug=corpusqa-128k-financial-chinese · How It Works · Data refreshed daily, snapshot 2026-09-25.