Skip to content

Benchmark

FLEURS-45 · Inferred language · Macro WER/CER

Scores are percentages. Lower is better.

Models measured
2
Scores recorded
2
Sources
1
IQ weight
No weight published

Score distribution

4.4%
Mean
4.6%
Median
0.25%
Std dev
4.1%
10th percentile
4.6%
90th percentile
4.1%
Min
4.1%4.6%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Voxtral Small Transcribe 3Voxtral 3 official release chart · macro WER/CER · 45 languages · inferred language· Reported by Mistral AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.4.1%
2Voxtral Mini Transcribe 3Voxtral 3 official release chart · macro WER/CER · 45 languages · inferred language· Reported by Mistral AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.4.6%

Data credits: 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.