AudioMC: leaderboard
AudioMultiChallenge benchmarks E2E spoken dialogue systems on multi-turn interaction, voice editing, and instruction retention.
Metric: Score (self-reported). Source: benchmarklist.com. Status: years away from saturation. 33 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) (High) | 66.8 |
| 2 | Inkling | 56.6 |
| 3 | Inkling Small | 54.9 |
| 4 | Gemini 2.5 Pro (Thinking) | 46.9 |
| 5 | Gemini 2.5 Flash (Thinking) | 40.04 |
| 6 | Gemini 2.5 Flash | 26.11 |
| 7 | Qwen3 Omni 30B A3B Instruct | 24.34 |
| 8 | Gemma 3n E4B (IT) | 15.49 |
| 9 | Phi-4 Multimodal Instruct | 15.49 |
Interactive version: theaggregate.ai/benchmark?slug=audiomc · How It Works · Data refreshed daily, snapshot 2026-09-05.