Skip to main content
BenchLM
Data

Scale Labs AudioMC (AudioMC)

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 — November 12, 2026 snapshot

We mirror the published scale score view for AudioMC. 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.

1

gemini-3.8-flash (high)

Google

60.4%
2

salesforce-launa-omni-1

Salesforce

59.7%
3

gemini-4-argon (high)

Google

58.4%

36 modelsMultimodal & GroundedCurrentDisplay onlyUpdated November 12, 2026 snapshot

Scale score table (36 models)

Scale score results for AudioMC
RankModel / configurationScoreParameters (B)Open / closed
1gemini-3.8-flash (high)Google
60.4%
Not reportedUnknown
2salesforce-launa-omni-1Salesforce
59.7%
Not reportedUnknown
3gemini-4-argon (high)Google
58.4%
Not reportedUnknown
4Inkling (Thinking)*Thinkingmachines
56.6%
Not reportedUnknown
5Inkling-small\nThinkingmachines
54.9%
Not reportedUnknown
6gemini-3-pro-preview (Thinking)*Google
54.6%
Not reportedUnknown
7gpt-realtime-2 (xHigh)OpenAI
48.5%
Not reportedUnknown
8gemini-2.5-pro (Thinking)*Google
46.9%
Not reportedUnknown
9tml-interaction-smallThinkingmachines
43.4%
Not reportedUnknown
10gemini-2.5-flash (Thinking)*Google
40.0%
Not reportedUnknown
11GPT Realtime 2OpenAI
37.6%
Not reportedClosed
12gemini-3.1-flash-live-preview (Thinking)†Google
36.1%
Not reportedUnknown
13gpt-realtime-1.5†OpenAI
34.7%
Not reportedUnknown
14gpt-realtime-1.5*\nOpenAI
29.9%
Not reportedUnknown
15gemini-3.1-flash-live-preview†Google
26.8%
Not reportedUnknown
16Voxtral-Small-24B-2507*Mistral
26.3%
Not reportedUnknown
17gemini-2.5-flash*Google
26.1%
Not reportedUnknown
18gpt-4o-audio-preview-2025-06-03*OpenAI
25.4%
Not reportedUnknown
19Qwen3-Omni-30B-A3B-Instruct†Alibaba
24.3%
Not reportedUnknown
20gpt-realtime-2025-08-28*OpenAI
23.4%
Not reportedUnknown
21gpt-4o-audio-preview-2025-06-03†OpenAI
23.2%
Not reportedUnknown
22gemini-2.5-flash-native-audio-preview-12-2025 (thinking)†Google
21.5%
Not reportedUnknown
23gpt-realtime-2025-08-28†OpenAI
20.4%
Not reportedUnknown
24MiMo-Audio-7B-Instruct (Thinking)*Other
19.7%
Not reportedUnknown
25MiMo-Audio-7B-Instruct*Other
18.6%
Not reportedUnknown
26gpt-realtime-mini-2025-12-15*OpenAI
16.6%
Not reportedUnknown
27gemma-3n-E4B-it*Google
15.5%
Not reportedUnknown
28Phi-4-multimodal-instruct*Microsoft
15.5%
Not reportedUnknown
29gpt-4o-mini-audio-preview-2024-12-17*OpenAI
14.8%
Not reportedUnknown
30gpt-realtime-mini-2025-12-15†OpenAI
13.9%
Not reportedUnknown
31gemini-2.5-flash-native-audio-preview-12-2025 (non-thinking)†Google
13.9%
Not reportedUnknown
32Kimi-Audio-7B-Instruct*Moonshot AI
13.7%
Not reportedUnknown
33gpt-4o-mini-audio-preview-2024-12-17†OpenAI
13.1%
Not reportedUnknown
34Qwen2.5-Omni-7B*Alibaba
11.9%
Not reportedUnknown
35Kimi-Audio-7B-Instruct†Moonshot AI
10.4%
Not reportedUnknown
36LFM2-Audio-1.5B†Other
9.3%
Not reportedUnknown

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: 36 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.

AudioMC on Scale Labs

How BenchLM shows AudioMC

BenchLM mirrors 36 published rows from Scale Labs’ public AudioMC 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.

Snapshot

36 published rowsScale Labs sourceDisplay only
AudioMC on Scale Labs

The published AudioMC 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 20.4 points, so the table still separates the published systems.

36 models have been evaluated on AudioMC. 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 is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About AudioMC

Year

2026

Tasks

36 published rows

Format

Published Scale leaderboard score

Difficulty

External agent and model evaluation

BenchLM mirrors 36 published rows from the AudioMC public table captured on November 12, 2026 snapshot.

Scale Labs leaderboardPublic benchmark source

Freshness and provenance

Version

AudioMC 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

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 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 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?

The November 12, 2026 snapshot snapshot contains 36 AI models.

Last updated: November 12, 2026 snapshot · mirrored from the public benchmark leaderboard

Know when it’s worth switching models

The model to choose, the cheaper alternative, and the release we would wait on.

Read a sample issue

Join 7,000+ subscribers.

One email each week. Unsubscribe anytime.