AudioMC (text output)
AudioMC answered in text. Scale AI.
As of 19 Sept 2026, Inkling Small leads AudioMC (text output) on BenchLeader with 54.9%, ahead of Gemini 3 Pro at 54.6%, across 17 model configurations with a published result.
- Published by
- Scale AI SEAL
- Category
- Multimodal
- Index weight
- Reference only
- Models
- 17
- Data as of
- 19 Sept 2026
Scale AI SEAL Leaderboards.
What the test looks like
The AudioMC questions with the model answering in text.
How it is scored
Accuracy, published by Scale AI.
What to keep in mind
Audio-input models only.
- 1Inkling Small54.9%
- 2Gemini 3 Pro (thinking)54.6%
- 3Gemini 2.5 Pro (thinking)46.9%
- 4Gemini 2.5 Flash (thinking)40.0%
- 5GPT Realtime 1.529.9%
- 6Voxtral Small 24B 250726.3%
- 7Gemini 2.5 Flash26.1%
- 8GPT 4o Audio25.4%
- 9GPT Realtime23.4%
- 10Mimo Audio 7B (thinking)19.7%
- 11Mimo Audio 7B18.6%
- 12GPT Realtime Mini16.6%
- 13Gemma 3n E4B15.5%
- 14Phi 4 Multimodal15.5%
- 15GPT 4o Mini Audio14.8%
17 of 17
| # | ||||
|---|---|---|---|---|
| 1 | Inkling SmallThinking Machinesopen ↗ | 54.9% | 56.3 | 2026-07-30 |
| 2 |  Gemini 3 ProthinkingGoogle | 54.6% | – | 2026-02-25 |
| 3 | Gemini 2.5 ProthinkingGoogle | 46.9% | – | 2026-02-25 |
| 4 | Gemini 2.5 FlashthinkingGoogle | 40.0% | 48.4 | 2026-02-25 |
| 5 |  GPT Realtime 1.5OpenAI | 29.9% | – | 2026-02-25 |
| 6 |  Voxtral Small 24B 2507Mistral AI | 26.3% | – | 2026-02-25 |
| 7 | Gemini 2.5 FlashGoogle | 26.1% | 52.5 | 2026-02-25 |
| 8 | GPT 4o AudioOpenAI | 25.4% | – | 2026-02-25 |
| 9 | GPT RealtimeOpenAI | 23.4% | – | 2026-02-25 |
| 10 | Mimo Audio 7BthinkingUnknown | 19.7% | – | 2026-02-25 |
| 11 | Mimo Audio 7BUnknown | 18.6% | – | 2026-02-25 |
| 12 | GPT Realtime MiniOpenAI | 16.6% | – | 2026-02-25 |
| 13 | Gemma 3n E4BGoogleopen | 15.5% | 36.4 | 2026-02-25 |
| 14 |  Phi 4 MultimodalMicrosoftopen | 15.5% | – | 2026-02-25 |
| 15 | GPT 4o Mini AudioOpenAI | 14.8% | – | 2026-02-25 |
| 16 |  Kimi Audio 7BMoonshot AI | 13.7% | – | 2026-02-25 |
| 17 |  Qwen2.5-Omni 7BAlibabaopen ↗ | 11.9% | – | 2026-02-25 |
Cite as: BenchLeader, “AudioMC (text output) leaderboard”, https://www.benchleader.com/benchmarks/scale_audiomc_text, data as of 19 Sept 2026.
AudioMC (text output): questions
- What does AudioMC (text output) measure?
- The AudioMC questions with the model answering in text. Scores are reported in percent of tasks solved; higher is better.
- Which AI model leads AudioMC (text output)?
- Inkling Small leads AudioMC (text output) with 54.9% as of 19 Sept 2026, ahead of Gemini 3 Pro at 54.6%.
- How many models have AudioMC (text output) results?
- 17 model configurations have a AudioMC (text output) result on BenchLeader, all taken from Scale AI SEAL.
- Who runs AudioMC (text output) and how often is it updated?
- AudioMC (text output) is published by Scale AI SEAL. BenchLeader re-reads the published results every morning and records the date each result was published.
- Does AudioMC (text output) count toward the BenchLeader Index?
- No. AudioMC (text output) is shown for reference but left out of the composite index.