Benchmarks
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Influence Estimation | Benchmarks Budgets k=1, 5, 10, 25 (Aggregated) | AUC (SR, dB)42.73 | 66 | |
| Zero-shot Evaluation | Zero-shot Benchmarks Average | Average Accuracy68.6 | 60 | |
| Zero-shot Evaluation | Benchmarks 0-shot | 0-shot Average Score73.33 | 33 | |
| Zero-shot language understanding | Zero-shot Benchmarks | Average Zero-shot Accuracy73.07 | 21 | |
| General Language Understanding | 10 Benchmarks Average (test) | Accuracy (Average)67.4 | 15 | |
| Visual Question Answering | 14 benchmarks 8 spatial and 6 real-world (test) | Average Accuracy (14 Benchmarks)74.5 | 14 | |
| General Multimodal Understanding | Combined 9 Benchmarks | Average Accuracy100 | 13 | |
| Image Classification | six benchmarks (macro-average) | Accuracy78.8 | 6 | |
| General Downstream Evaluation | 19 short-context benchmarks | ShortAvg41.32 | 6 | |
| Agentic Trajectory Question Answering | Benchmarks 12 task columns | Average Rank3.1 | 5 |
Showing 10 of 10 rows