| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| ATIS (test) | Bi-model | Slot F196.89 | 18 | 4mo ago | |
| MAC-SLU | SFL-MTSC | Overall Accuracy4.69 | 16 | 1mo ago | |
| FSC (test) | Cascaded | Intent Accuracy100 | 16 | 4mo ago | |
| ATIS | Cascaded | Slot F196.1 | 16 | 4mo ago | |
| SNIPS | Joint BERT | Slot F197 | 15 | 4mo ago | |
| MEDIA | FlauBERT-B | SLU CER10.2 | 14 | 4mo ago | |
| Fluent Speech Commands (test) | 3D-CNN+LSTM+CE | Accuracy99.26 | 12 | 4mo ago | |
| BBA | Qwen3-Omni-30B-A3B-Thinking | LBBA Score96.8 | 11 | 2mo ago | |
| MixSNIPS | SSRAN | Intent Accuracy98.4 | 10 | 4mo ago | |
| SLURP 6 tasks | Avg Accuracy84.41 | 9 | 4mo ago | ||
| SLURP 3 tasks | Average Accuracy84.41 | 9 | 4mo ago | ||
| FSC 3 tasks | Avg Accuracy99.28 | 9 | 4mo ago | ||
| SLURP Oracle | CORTIS | Intent Accuracy91.57 | 8 | 1mo ago | |
| CrossWOZ | MLM + SBO + PMO w/ NP Sampling | Intent F196.97 | 7 | 4mo ago | |
| in-house SLU dataset | FANS-c | RI-ICER0 | 6 | 4mo ago | |
| SILICONE 1.0 (test) | HT | Avg Score74.3 | 6 | 4mo ago | |
| SLURP (test) | MATE | Scenario Accuracy78.76 | 5 | 4mo ago | |
| MultiATIS++ (test) | GL-CLEF | Accuracy (EN)88.02 | 5 | 4mo ago | |
| Internal Traffic Dataset hard (test) | transformer-based E2E SLU | ICER (Relative Improvement)12.9 | 5 | 4mo ago | |
| Internal Traffic Dataset (regular test) | transformer-based E2E SLU | ICER Improvement (%)9.3 | 5 | 4mo ago | |
| FSC (test) | CORTIS | EM (Oracle)100 | 4 | 1mo ago | |
| SLURP 0 dB | CORTIS | Intent Accuracy33.29 | 4 | 1mo ago | |
| SLURP 2.5 dB | CORTIS | Intent Accuracy46.68 | 4 | 1mo ago | |
| SLURP 5 dB | CORTIS | Intent Accuracy59.47 | 4 | 1mo ago | |
| SLURP 10 dB | CORTIS | Intent Accuracy74.94 | 4 | 1mo ago |
