Skip to main content
BenchLM
Data

Scale Labs AudioMC – Audio Output (AudioMC – Audio 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 – Audio Output — November 12, 2026 snapshot

We mirror the published scale score view for AudioMC – Audio Output. gpt-realtime-2 (xHigh) leads the public snapshot at 48.5%, followed by tml-interaction-small (43.4%) and GPT Realtime 2 (37.6%). We do not use these results to rank models overall.

1

gpt-realtime-2 (xHigh)

OpenAI

48.5%
2

tml-interaction-small

Thinkingmachines

43.4%
3Closed

GPT Realtime 2

OpenAI

37.6%
Context 128K

15 modelsMultimodal & GroundedCurrentDisplay onlyUpdated November 12, 2026 snapshot

Scale score table (15 models)

Scale score results for AudioMC – Audio Output
RankModel / configurationScoreParameters (B)Open / closed
1gpt-realtime-2 (xHigh)OpenAI
48.5%
Not reportedUnknown
2tml-interaction-smallThinkingmachines
43.4%
Not reportedUnknown
3GPT Realtime 2OpenAI
37.6%
Not reportedClosed
4gemini-3.1-flash-live-preview (Thinking)Google
36.1%
Not reportedUnknown
5GPT Realtime 1.5OpenAI
34.7%
Not reportedClosed
6Gemini 3.1 Flash Live PreviewGoogle
26.8%
Not reportedClosed
7Qwen3-Omni-30B-A3B-InstructAlibaba
24.3%
Not reportedOpen
8gpt-4o-audio-preview-2025-06-03OpenAI
23.2%
Not reportedUnknown
9gemini-2.5-flash-native-audio-preview-12-2025 (thinking)Google
21.5%
Not reportedUnknown
10GPT RealtimeOpenAI
20.4%
Not reportedClosed
11GPT Realtime miniOpenAI
13.9%
Not reportedClosed
12gemini-2.5-flash-native-audio-preview-12-2025 (non-thinking)Google
13.9%
Not reportedUnknown
13gpt-4o-mini-audio-preview-2024-12-17OpenAI
13.1%
Not reportedUnknown
14Kimi-Audio-7B-InstructMoonshot AI
10.4%
Not reportedUnknown
15LFM2-Audio-1.5BOther
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: 15 sourced rows are currently displayable on this page; the leading published row is gpt-realtime-2 (xHigh) at 48.5%.

Honest limit: This Scale table is display-only context, not benchmark provenance or a weighted model-only comparison.

AudioMC – Audio Output on Scale Labs

How BenchLM shows AudioMC – Audio Output

BenchLM mirrors 15 published rows from Scale Labs’ public AudioMC – Audio 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. Scale has not added a row to this board since May 2026.

Snapshot

15 published rowsScale Labs sourceNo new rowsDisplay only
AudioMC – Audio Output on Scale Labs

The published AudioMC – Audio Output snapshot places gpt-realtime-2 (xHigh) first at 48.5%. The third row is 10.8 points behind. The broader top-10 range is 28.1 points, so the table still separates the published systems.

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

About AudioMC – Audio Output

Year

2026

Tasks

15 published rows

Format

Published Scale leaderboard score

Difficulty

External agent and model evaluation

BenchLM mirrors 15 published rows from the AudioMC – Audio Output public table captured on November 12, 2026 snapshot.

Scale Labs leaderboardPublic benchmark source

Freshness and provenance

Version

AudioMC – Audio Output 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 – Audio 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 – Audio Output snapshot?

gpt-realtime-2 (xHigh) currently leads the published AudioMC – Audio Output snapshot with 48.5% scale score. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on AudioMC – Audio Output?

The November 12, 2026 snapshot snapshot contains 15 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.