Average across models
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multi-path Speculative Decoding | Average across models (Qwen, Gemma, Llama) (test) | Throughput (tokens/s)16.69 | 6 | |
| VLA Hijacking | Average across Models Main Results (5 tasks) | ASR52.54 | 5 |
Showing 2 of 2 rows