# Scale Labs AudioMC – Audio Output (AudioMC – Audio Output)

> A Scale Labs public leaderboard mirrored as display-only reference data. It does not affect BenchLM rankings.

Canonical page: https://benchlm.ai/benchmarks/scale-audiomc-audio

- Category: [Multimodal & Grounded](/multimodal-grounded)
- Last updated: September 29, 2026 snapshot

## About AudioMC – Audio Output

- Year: 2026
- Tasks: 15 published rows
- Format: Published Scale leaderboard score
- Difficulty: External agent and model evaluation
- Paper: [Scale Labs leaderboard](https://labs.scale.com/leaderboard/audiomc-audio)

BenchLM mirrors 15 published rows from the AudioMC – Audio Output public table captured on September 29, 2026 snapshot.

AudioMC – Audio Output is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (15 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [gpt-realtime-2 (xHigh)](https://labs.scale.com/leaderboard/audiomc-audio) | OpenAI | 48.45% |
| 2 | [tml-interaction-small](https://labs.scale.com/leaderboard/audiomc-audio) | Thinkingmachines | 43.36% |
| 3 | [GPT Realtime 2](/models/gpt-realtime-2) | OpenAI | 37.61% |
| 4 | [gemini-3.1-flash-live-preview (Thinking)](https://labs.scale.com/leaderboard/audiomc-audio) | Google | 36.06% |
| 5 | [GPT Realtime 1.5](/models/gpt-realtime-1-5) | OpenAI | 34.73% |
| 6 | [Gemini 3.1 Flash Live Preview](/models/gemini-3-1-flash-live-preview) | Google | 26.77% |
| 7 | [Qwen3-Omni-30B-A3B-Instruct](/models/qwen3-omni-30b-a3b-instruct) | Alibaba | 24.34% |
| 8 | [gpt-4o-audio-preview-2025-06-03](https://labs.scale.com/leaderboard/audiomc-audio) | OpenAI | 23.23% |
| 9 | [gemini-2.5-flash-native-audio-preview-12-2025 (thinking)](https://labs.scale.com/leaderboard/audiomc-audio) | Google | 21.46% |
| 10 | [GPT Realtime](/models/gpt-realtime) | OpenAI | 20.35% |
| 11 | [GPT Realtime mini](/models/gpt-realtime-mini) | OpenAI | 13.94% |
| 12 | [gemini-2.5-flash-native-audio-preview-12-2025 (non-thinking)](https://labs.scale.com/leaderboard/audiomc-audio) | Google | 13.90% |
| 13 | [gpt-4o-mini-audio-preview-2024-12-17](https://labs.scale.com/leaderboard/audiomc-audio) | OpenAI | 13.05% |
| 14 | [Kimi-Audio-7B-Instruct](https://labs.scale.com/leaderboard/audiomc-audio) | Moonshot AI | 10.40% |
| 15 | [LFM2-Audio-1.5B](https://labs.scale.com/leaderboard/audiomc-audio) | Other | 9.29% |

## FAQ

### What does AudioMC – Audio Output measure?

A Scale Labs public leaderboard mirrored as display-only reference data. It does not affect BenchLM rankings.

### Which model leads the published AudioMC – Audio Output snapshot?

gpt-realtime-2 (xHigh) currently leads the published AudioMC – Audio Output snapshot with a score of 48.45%.

### How many models are evaluated on AudioMC – Audio Output?

The September 29, 2026 snapshot contains 15 AI models.

### Does AudioMC – Audio Output affect BenchLM's overall score?

Not directly. AudioMC – Audio Output is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.