PitchBench - Tone Onset and Offset: leaderboard
Metric: Accuracy (%; report the onset and offset of a single tone within 250 ms). Source: arxiv.org. Saturation forecast: Around 2030. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.5 Omni Plus | 13.1 |
| 2 | Qwen3.5 Omni Flash | 9.4 |
| 3 | Gemini 3 Flash | 2.5 |
| 4 | GPT-4o Audio | 0.8 |
| 5 | Gemini 3.1 Pro (Preview) | 0 |
Interactive version: theaggregate.ai/benchmark?slug=pitchbench-tone-onset-and-offset · How It Works · Data refreshed daily, snapshot 2026-09-26.