| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| UniICL-Bench | UniICL | Perception Score80.9 | 33 | 2mo ago | |
| MMMU | Qwen2.5-VL-32B | MMMU Score75.1 | 20 | 2mo ago | |
| C3 | Score68.94 | 20 | 3mo ago | ||
| XSum | Score46.76 | 20 | 3mo ago | ||
| RACE Middle | Score67.27 | 20 | 3mo ago | ||
| MathVista | Qwen2.5-VL-32B | MathVista Score84.7 | 12 | 2mo ago | |
| Algospeak Phonetic strategy | Threshold x0 (IMUM@0.5)6 | 7 | 26d ago | ||
| Algospeak Code strategy | Estimated Threshold x0 (IMUM@0.5)1.1699 | 7 | 26d ago | ||
| Algospeak Paraphrase strategy | Estimated Threshold x0 (IMUM@0.5)2.7983 | 7 | 26d ago | ||
| Algospeak Emotion strategy | Estimated Threshold x0 (IMUM@0.5)4.3287 | 7 | 26d ago | ||
| Algospeak Abbreviation strategy | Estimated Threshold x0 (IMUM@0.5)6 | 7 | 26d ago | ||
| Algospeak New word strategy | Estimated Threshold x0 (IMUM@0.5)6 | 7 | 26d ago | ||
| Algospeak Unknown word strategy | Estimated Threshold x0 (IMUM@0.5)6 | 7 | 26d ago |
