Skip to content

Benchmark

FLEURS-45 · Forced 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

4.3%
Mean
4.5%
Median
0.25%
Std dev
4%
10th percentile
4.5%
90th percentile
4%
Min
4%4.5%
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 · forced language· Reported by Mistral AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.4%
2Voxtral Mini Transcribe 3Voxtral 3 official release chart · macro WER/CER · 45 languages · forced language· Reported by Mistral AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.4.5%

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.