# Scale Labs AudioMC – Text Output (AudioMC – Text 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-text

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

## About AudioMC – Text Output

- Year: 2026
- Tasks: 18 published rows
- Format: Published Scale leaderboard score
- Difficulty: External agent and model evaluation
- Paper: [Scale Labs leaderboard](https://labs.scale.com/leaderboard/audiomc-text)

BenchLM mirrors 18 published rows from the AudioMC – Text Output public table captured on September 29, 2026 snapshot.

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

## Leaderboard (18 models)

| Rank | Model | Creator | Score |
|------|-------|---------|-------|
| 1 | [Inkling (Thinking)](https://labs.scale.com/leaderboard/audiomc-text) | Thinkingmachines | 56.64% |
| 2 | [Inkling-small\n](https://labs.scale.com/leaderboard/audiomc-text) | Thinkingmachines | 54.87% |
| 3 | [gemini-3-pro-preview (Thinking)](https://labs.scale.com/leaderboard/audiomc-text) | Google | 54.65% |
| 4 | [gemini-2.5-pro (Thinking)](https://labs.scale.com/leaderboard/audiomc-text) | Google | 46.90% |
| 5 | [gemini-2.5-flash (Thinking)](https://labs.scale.com/leaderboard/audiomc-text) | Google | 40.04% |
| 6 | [GPT Realtime 1.5](/models/gpt-realtime-1-5) | OpenAI | 29.87% |
| 7 | [Voxtral-Small-24B-2507](https://labs.scale.com/leaderboard/audiomc-text) | Mistral | 26.33% |
| 8 | [Gemini 2.5 Flash](/models/gemini-2-5-flash) | Google | 26.11% |
| 9 | [gpt-4o-audio-preview-2025-06-03](https://labs.scale.com/leaderboard/audiomc-text) | OpenAI | 25.44% |
| 10 | [GPT Realtime](/models/gpt-realtime) | OpenAI | 23.45% |
| 11 | [MiMo-Audio-7B-Instruct (Thinking)](https://labs.scale.com/leaderboard/audiomc-text) | Other | 19.69% |
| 12 | [MiMo-Audio-7B-Instruct](https://labs.scale.com/leaderboard/audiomc-text) | Other | 18.58% |
| 13 | [GPT Realtime mini](/models/gpt-realtime-mini) | OpenAI | 16.59% |
| 14 | [Phi-4 Multimodal Instruct](/models/phi-4-multimodal-instruct) | Microsoft | 15.49% |
| 15 | [gemma-3n-E4B-it](https://labs.scale.com/leaderboard/audiomc-text) | Google | 15.49% |
| 16 | [gpt-4o-mini-audio-preview-2024-12-17](https://labs.scale.com/leaderboard/audiomc-text) | OpenAI | 14.82% |
| 17 | [Kimi-Audio-7B-Instruct](https://labs.scale.com/leaderboard/audiomc-text) | Moonshot AI | 13.72% |
| 18 | [Qwen2.5-Omni 7B](/models/qwen2-5-omni-7b) | Alibaba | 11.95% |

## FAQ

### What does AudioMC – Text 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 – Text Output snapshot?

Inkling (Thinking) currently leads the published AudioMC – Text Output snapshot with a score of 56.64%.

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

The September 29, 2026 snapshot contains 18 AI models.

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

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