English scenario
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
English Scenario Aggregated
0.7Hallucination Rate
8
English Scenario Aggregate
0.7Hallucination Rate
8
English scenario Multi-app Advanced Instruction
100Completion Rate (CR)
3
English scenario External app Advanced Instruction
97.1Completion Rate (CR)
3
English scenario External app Basic Instruction
100Completion Rate (CR)
3
English scenario System app Advanced Instruction
85.3Completion Rate (CR)
3
English scenario System app Basic Instruction
100Completion Rate (CR)
3
English scenario Multi-app Basic Instruction
100Completion Rate (CR)
2