Scale Labs AudioMC – Text Output (AudioMC – Text Output)
We show this table for reference; we do not rank on it.
A Scale Labs public leaderboard mirrored as display-only reference data. It does not affect BenchLM rankings.
Scale score on AudioMC – Text Output — November 12, 2026 snapshot
We mirror the published scale score view for AudioMC – Text Output. gemini-3.8-flash (high) leads the public snapshot at 60.4%, followed by salesforce-launa-omni-1 (59.7%) and gemini-4-argon (high) (58.4%). We do not use these results to rank models overall.
gemini-3.8-flash (high)
salesforce-launa-omni-1
Salesforce
gemini-4-argon (high)
21 modelsMultimodal & GroundedCurrentDisplay onlyUpdated November 12, 2026 snapshot
Scale score table (21 models)
| Rank | Model / configuration | Score | Parameters (B) | Open / closed |
|---|---|---|---|---|
| 1 | gemini-3.8-flash (high)Google | 60.4% | Not reported | Unknown |
| 2 | salesforce-launa-omni-1Salesforce | 59.7% | Not reported | Unknown |
| 3 | gemini-4-argon (high)Google | 58.4% | Not reported | Unknown |
| 4 | Inkling (Thinking)Thinkingmachines | 56.6% | Not reported | Unknown |
| 5 | Inkling-small\nThinkingmachines | 54.9% | Not reported | Unknown |
| 6 | gemini-3-pro-preview (Thinking)Google | 54.6% | Not reported | Unknown |
| 7 | gemini-2.5-pro (Thinking)Google | 46.9% | Not reported | Unknown |
| 8 | gemini-2.5-flash (Thinking)Google | 40.0% | Not reported | Unknown |
| 9 | GPT Realtime 1.5OpenAI | 29.9% | Not reported | Closed |
| 10 | Voxtral-Small-24B-2507Mistral | 26.3% | Not reported | Unknown |
| 11 | Gemini 2.5 FlashGoogle | 26.1% | Not reported | Closed |
| 12 | gpt-4o-audio-preview-2025-06-03OpenAI | 25.4% | Not reported | Unknown |
| 13 | GPT RealtimeOpenAI | 23.4% | Not reported | Closed |
| 14 | MiMo-Audio-7B-Instruct (Thinking)Other | 19.7% | Not reported | Unknown |
| 15 | MiMo-Audio-7B-InstructOther | 18.6% | Not reported | Unknown |
| 16 | GPT Realtime miniOpenAI | 16.6% | Not reported | Closed |
| 17 | Phi-4 Multimodal InstructMicrosoft | 15.5% | Not reported | Open |
| 18 | gemma-3n-E4B-itGoogle | 15.5% | Not reported | Unknown |
| 19 | gpt-4o-mini-audio-preview-2024-12-17OpenAI | 14.8% | Not reported | Unknown |
| 20 | Kimi-Audio-7B-InstructMoonshot AI | 13.7% | Not reported | Unknown |
| 21 | Qwen2.5-Omni 7BAlibaba | 11.9% | Not reported | Open |
How to read this leaderboard
Compare the published configurations as complete evaluation systems. The source can combine a base model, agent scaffold, tools, budget, and inference setting in each result.
Operator receipt: 21 sourced rows are currently displayable on this page; the leading published row is gemini-3.8-flash (high) at 60.4%.
Honest limit: This Scale table is display-only context, not benchmark provenance or a weighted model-only comparison.
How BenchLM shows AudioMC – Text Output
BenchLM mirrors 21 published rows from Scale Labs’ public AudioMC – Text Output leaderboard, captured on November 12, 2026 snapshot.
The table is display only. It is useful context for a published agent or model configuration, but it does not enter BenchLM’s overall or category rankings.
The published AudioMC – Text Output snapshot places gemini-3.8-flash (high) first at 60.4%. The third row is 2.0 points behind. The broader top-10 range is 34.1 points, so the table still separates the published systems.
21 models have been evaluated on AudioMC – Text Output. The benchmark falls in the Multimodal & Grounded category. We keep external benchmark mirrors separate from the weighted global scoring system, so these results remain source-specific evidence. AudioMC – Text Output is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About AudioMC – Text Output
Year
2026
Tasks
21 published rows
Format
Published Scale leaderboard score
Difficulty
External agent and model evaluation
BenchLM mirrors 21 published rows from the AudioMC – Text Output public table captured on November 12, 2026 snapshot.
Freshness and provenance
Version
AudioMC – Text Output 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
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?
gemini-3.8-flash (high) currently leads the published AudioMC – Text Output snapshot with 60.4% scale score. BenchLM shows this benchmark for display only and does not use it in overall rankings.
How many models are evaluated on AudioMC – Text Output?
The November 12, 2026 snapshot snapshot contains 21 AI models.
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 7,000+ subscribers.
One email each week. Unsubscribe anytime.