| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| LongStoryQA Large | SitEmb-v1.5-Qwen3 (QA) | F1 Score61.9 | 12 | 1mo ago | |
| NoCha Public | SitEmb-v1.5-Qwen3 (QA) | Pair Accuracy55.6 | 12 | 1mo ago | |
| DetectiveQA | SitEmb-v1.5-Qwen3 (QA) | Accuracy82.3 | 12 | 1mo ago | |
| ∞Bench En.MC | SitEmb-v1.5-Qwen3 (QA) | Accuracy90 | 12 | 1mo ago |