Skip to content

Benchmark

Full Duplex Bench v1.5 · Interactivity

Scores are percentages. Higher is better.

Models and systems measured
3
Scores recorded
3
Sources
1
IQ weight
No weight published

Score distribution

57.8%
Mean
47.8%
Median
15.8%
Std dev
45.4%
10th percentile
80.1%
90th percentile
45.4%
Min
45.4%80.1%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#Model or systemScore
1GPT-Live 1OpenAI release chart · background speech and interruption evaluation· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.80.1%
2GPT Realtime 2OpenAI release chart · background speech and interruption evaluation· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.47.8%

Not ranked

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

Model or systemScore
GPT-Realtime-2.1OpenAI release chart · background speech and interruption evaluation· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.45.4%

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.