# Scale Labs AudioMC (AudioMC)

> 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

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

## About AudioMC

- Year: 2026
- Tasks: 34 published rows
- Format: Published Scale leaderboard score
- Difficulty: External agent and model evaluation
- Paper: [Scale Labs leaderboard](https://labs.scale.com/leaderboard/audiomc)

BenchLM mirrors 34 published rows from the AudioMC public table captured on September 29, 2026 snapshot.

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

## Leaderboard (34 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [gemini-3.8-flash (high)](https://labs.scale.com/leaderboard/audiomc) | Google | 60.40% |
| 2 | [Inkling (Thinking)*](https://labs.scale.com/leaderboard/audiomc) | Thinkingmachines | 56.64% |
| 3 | [Inkling-small\n](https://labs.scale.com/leaderboard/audiomc) | Thinkingmachines | 54.87% |
| 4 | [gemini-3-pro-preview (Thinking)*](https://labs.scale.com/leaderboard/audiomc) | Google | 54.65% |
| 5 | [gpt-realtime-2 (xHigh)](https://labs.scale.com/leaderboard/audiomc) | OpenAI | 48.45% |
| 6 | [gemini-2.5-pro (Thinking)*](https://labs.scale.com/leaderboard/audiomc) | Google | 46.90% |
| 7 | [tml-interaction-small](https://labs.scale.com/leaderboard/audiomc) | Thinkingmachines | 43.36% |
| 8 | [gemini-2.5-flash (Thinking)*](https://labs.scale.com/leaderboard/audiomc) | Google | 40.04% |
| 9 | [GPT Realtime 2](/models/gpt-realtime-2) | OpenAI | 37.61% |
| 10 | [gemini-3.1-flash-live-preview (Thinking)†](https://labs.scale.com/leaderboard/audiomc) | Google | 36.06% |
| 11 | [gpt-realtime-1.5†](https://labs.scale.com/leaderboard/audiomc) | OpenAI | 34.73% |
| 12 | [gpt-realtime-1.5*\n](https://labs.scale.com/leaderboard/audiomc) | OpenAI | 29.87% |
| 13 | [gemini-3.1-flash-live-preview†](https://labs.scale.com/leaderboard/audiomc) | Google | 26.77% |
| 14 | [Voxtral-Small-24B-2507*](https://labs.scale.com/leaderboard/audiomc) | Mistral | 26.33% |
| 15 | [gemini-2.5-flash*](https://labs.scale.com/leaderboard/audiomc) | Google | 26.11% |
| 16 | [gpt-4o-audio-preview-2025-06-03*](https://labs.scale.com/leaderboard/audiomc) | OpenAI | 25.44% |
| 17 | [Qwen3-Omni-30B-A3B-Instruct†](https://labs.scale.com/leaderboard/audiomc) | Alibaba | 24.34% |
| 18 | [gpt-realtime-2025-08-28*](https://labs.scale.com/leaderboard/audiomc) | OpenAI | 23.45% |
| 19 | [gpt-4o-audio-preview-2025-06-03†](https://labs.scale.com/leaderboard/audiomc) | OpenAI | 23.23% |
| 20 | [gemini-2.5-flash-native-audio-preview-12-2025 (thinking)†](https://labs.scale.com/leaderboard/audiomc) | Google | 21.46% |
| 21 | [gpt-realtime-2025-08-28†](https://labs.scale.com/leaderboard/audiomc) | OpenAI | 20.35% |
| 22 | [MiMo-Audio-7B-Instruct (Thinking)*](https://labs.scale.com/leaderboard/audiomc) | Other | 19.69% |
| 23 | [MiMo-Audio-7B-Instruct*](https://labs.scale.com/leaderboard/audiomc) | Other | 18.58% |
| 24 | [gpt-realtime-mini-2025-12-15*](https://labs.scale.com/leaderboard/audiomc) | OpenAI | 16.59% |
| 25 | [gemma-3n-E4B-it*](https://labs.scale.com/leaderboard/audiomc) | Google | 15.49% |
| 26 | [Phi-4-multimodal-instruct*](https://labs.scale.com/leaderboard/audiomc) | Microsoft | 15.49% |
| 27 | [gpt-4o-mini-audio-preview-2024-12-17*](https://labs.scale.com/leaderboard/audiomc) | OpenAI | 14.82% |
| 28 | [gpt-realtime-mini-2025-12-15†](https://labs.scale.com/leaderboard/audiomc) | OpenAI | 13.94% |
| 29 | [gemini-2.5-flash-native-audio-preview-12-2025 (non-thinking)†](https://labs.scale.com/leaderboard/audiomc) | Google | 13.90% |
| 30 | [Kimi-Audio-7B-Instruct*](https://labs.scale.com/leaderboard/audiomc) | Moonshot AI | 13.72% |
| 31 | [gpt-4o-mini-audio-preview-2024-12-17†](https://labs.scale.com/leaderboard/audiomc) | OpenAI | 13.05% |
| 32 | [Qwen2.5-Omni-7B*](https://labs.scale.com/leaderboard/audiomc) | Alibaba | 11.95% |
| 33 | [Kimi-Audio-7B-Instruct†](https://labs.scale.com/leaderboard/audiomc) | Moonshot AI | 10.40% |
| 34 | [LFM2-Audio-1.5B†](https://labs.scale.com/leaderboard/audiomc) | Other | 9.29% |

## FAQ

### What does AudioMC measure?

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

### Which model leads the published AudioMC snapshot?

gemini-3.8-flash (high) currently leads the published AudioMC snapshot with a score of 60.40%.

### How many models are evaluated on AudioMC?

The September 29, 2026 snapshot contains 34 AI models.

### Does AudioMC affect BenchLM's overall score?

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