Skip to content

Benchmark

Big Bench Audio

Scores are percentages. Higher is better.

Models measured
2
Scores recorded
2
Sources
2
IQ weight
No weight published

Score distribution

96.3%
Mean
98.5%
Median
2.3%
Std dev
94%
10th percentile
98.5%
90th percentile
94%
Min
94%98.5%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Grok Voice 3.0· LLM Stats data98.5%
2MiMo V2 OmniXiaomi MiMo-V2-Omni release table · speech reasoning· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.94%

Data credits: Data by LLM Stats · BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.