SpeakerSleuth - Detection: leaderboard
Metric: Balanced accuracy (%; 0.5 x (S1 + mean(S2, S3)) over 606 dialogues per scenario). Source: arxiv.org. Saturation forecast: Around July 2028. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 2.5 Pro | 64.7 |
| 2 | Gemini 2.5 Flash | 63.1 |
| 3 | Gemini 2.5 Flash Lite | 55.3 |
| 4 | Phi-4 Multimodal Instruct | 51.7 |
| 5 | Gemma 3n E4B | 50.4 |
Interactive version: theaggregate.ai/benchmark?slug=speakersleuth-detection · How It Works · Data refreshed daily, snapshot 2026-09-25.