| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Aggregated Benchmarks (AIME, ARC, GSM8K, HE, MMLU, IT, RU, BFCL) | Overall Average Rank2.4 | 16 | 23d ago | ||
| SummEval | BARTSCORE-CNN | Spearman Correlation (COH)0.448 | 10 | 3mo ago | |
| AgentEvalBench 1.0 (test) | EvalAgent | URF85 | 8 | 21d ago | |
| AgentEvalBench | EvalAgent | URF83.8 | 8 | 21d ago | |
| Overall Average | Ultra-Dense Prompting | Accuracy Improvement9.7 | 5 | 1mo ago |