Polaris
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Mathematical Reasoning | Polaris (test) | Cumulative Rollouts (M)4.92 | 16 | |
| Human Correlation for Image Captioning Evaluation | Polaris | Kendall's Tau-c63.2 | 16 | |
| Correlation with human judgments | Polaris (test) | Kendall's Tau-c0.578 | 16 | |
| Multimodal Preference Evaluation | Polaris | tau_c57.8 | 10 | |
| Mathematical Reasoning and Coding | Polaris | Peak Accuracy@848.79 | 6 | |
| Jailbreak Attack Evaluation | POLARIS | Attack Success Count520 | 2 |
Showing 6 of 6 rows