| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Interruption Handling | Full-Duplex-Bench | GPT-4o Score4.59 | 18 | |
| Turn Taking | Full-Duplex-Bench | TOR99.2 | 17 | |
| Pause Handling | Full-Duplex-Bench Candor | TOR1 | 13 | |
| Backchanneling | Full-Duplex-Bench | TOR100 | 11 | |
| Pause Handling | Full-Duplex-Bench Synthetic | TOR99 | 11 | |
| Full-duplex Speech Interaction Latency Analysis | Full-Duplex-Bench v1.5 | Stop Latency (Mean)0.68 | 8 | |
| Duplex Dialogue Turn-Taking | Full-Duplex-Bench | Synthetic TOR for Pause Handling0.058 | 8 | |
| Full-Duplex Speech Interaction | Full-Duplex-Bench Background Speech 1.5 | Respond Rate93 | 7 | |
| Full-Duplex Speech Interaction | Full-Duplex-Bench 1.5 (Talking to Other) | Response Rate91 | 7 | |
| Full-Duplex Speech Interaction | Full-Duplex-Bench User Backchannel 1.5 | Respond Rate7 | 7 | |
| Full-Duplex Speech Interaction | Full-Duplex-Bench User Interruption 1.5 | Response Rate78 | 7 | |
| Voice Cloning Speaker Similarity | Full-Duplex-Bench | SSIM57 | 5 | |
| Dialog Naturalness | Full-Duplex-Bench | DMOS3.9 | 5 | |
| User Interruption | Full-Duplex-Bench 1.0 | TOR1 | 2 | |
| Backchannel | Full-Duplex-Bench 1.0 | TOR1 | 2 | |
| Overlap Handling Evaluation | Full-Duplex-Bench User Interruption v1.5 | STOI0.97 | 2 | |
| Overlap Handling Evaluation | Full-Duplex-Bench User Backchannel v1.5 | STOI91 | 2 | |
| Overlap Handling Evaluation | Full-Duplex-Bench Talking to Other v1.5 | STOI0.96 | 2 | |
| Overlap Handling Evaluation | Full-Duplex-Bench Background Speech v1.5 | STOI0.98 | 2 | |
| Turn Taking | Full-Duplex-Bench Bilingual Chinese | TOR99.4 | 2 | |
| Turn Taking | Full-Duplex-Bench EN | Latency (ms)205 | 1 | |
| Dialog Naturalness | Full-Duplex-Bench User Interruption category | Metric- | 0 |