Skip to content
AIMODELRACE
Multimodal · sub-raceClear lead

Speech & Audio race

Native speech understanding: transcription, tone, speakers and sound events.

Leader
Gemini 4 Argon
Margin
1.2 pts
1.4% ahead
Weeks at #1
1
in a row
Changes
5
in 2026

Warming up the track…

Oct 19, 2026Gemini 4 Argon leads
2025Apr ’25Jul ’25Oct ’252026Apr ’26Jul ’26Oct ’26

Score history

Top 6 today over the leader's frontier · click to jump to a week

#1 frontierGemini 4 ArgonGPT-6.1 SolGPT-6 AstraMuse WonderGPT-5.53.5 Flash
65.070.075.080.085.090.02025Apr ’25Jul ’25Oct ’252026Apr ’26Jul ’26Oct ’26

Reigns at #1

Longest: 3.1 Pro, 24 weeks (from Feb 2026).

Sibling races

More multimodal races

Why this race matters

Voice is becoming the default interface for assistants.

How it is scored

Accuracy on native-audio reasoning tasks.

Unit: percentHigher is betterPhoto finish under 0.5 ptsDominant over 3.0 pts

Data provenance

  • Big Bench Audio / MMAU

    Spoken reasoning and audio understanding.

Scores here are illustrative placeholders that mimic real benchmark patterns. Swap in live data through the score provider. Methodology