English scenario
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Hallucination Mitigation | English Scenario Aggregated | Hallucination Rate0.7 | 8 | |
| Automatic Speech Recognition | English Scenario Aggregate | Hallucination Rate0.7 | 8 | |
| Mobile device operation | English scenario Multi-app Advanced Instruction | Completion Rate (CR)100 | 3 | |
| Mobile device operation | English scenario External app Advanced Instruction | Completion Rate (CR)97.1 | 3 | |
| Mobile device operation | English scenario External app Basic Instruction | Completion Rate (CR)100 | 3 | |
| Mobile device operation | English scenario System app Advanced Instruction | Completion Rate (CR)85.3 | 3 | |
| Mobile device operation | English scenario System app Basic Instruction | Completion Rate (CR)100 | 3 | |
| Mobile device operation | English scenario Multi-app Basic Instruction | Completion Rate (CR)100 | 2 |
Showing 8 of 8 rows