SEAL - AudioMultiChallenge - Audio Output — leaderboard
Metric: Score. Source: scale.com. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | gpt-realtime-2 (xHigh) | 48.45 |
| 2 | tml-interaction-small | 43.36 |
| 3 | gpt-realtime-2 | 37.61 |
| 4 | gemini-3.1-flash-live-preview (Thinking) | 36.06 |
| 5 | gpt-realtime-1.5 | 34.73 |
| 6 | gemini-3.1-flash-live-preview | 26.77 |
| 7 | Qwen3-Omni-30B-A3B-Instruct | 24.34 |
| 8 | gpt-4o-audio-preview-2025-06-03 | 23.23 |
| 9 | gemini-2.5-flash-native-audio-preview-12-2025 (thinking) | 21.46 |
| 10 | gpt-realtime-2025-08-28 | 20.35 |
Interactive version: theaggregate.ai/benchmark?slug=seal-audiomultichallenge-audio-output · How the rankings work · Data refreshed daily, snapshot 2026-07-22.