| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Security | Cost ($)0.01 | 15 | 3mo ago | ||
| Science | Cost ($)0.0276 | 15 | 3mo ago | ||
| Data | Cost ($)0.0136 | 15 | 3mo ago | ||
| Exp-2 Dynamic | Average Latency4,823 | 12 | 6d ago | ||
| Exp-1 Warmup | Average Latency5,018.93 | 12 | 6d ago | ||
| OlympusBench single-task setting | Olympus | Accuracy94.75 | 3 | 3mo ago | |
| OlympusBench chain-of-action setting | Olympus | Exact Difference (ED)18 | 3 | 3mo ago |
