Skip to content

Benchmark

Artificial Analysis WER Index · Mistral chart

Scores are percentages. Lower is better.

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

Score distribution

2.2%
Mean
2.2%
Median
0.06%
Std dev
2.1%
10th percentile
2.2%
90th percentile
2.1%
Min
2.1%2.2%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Voxtral Small Transcribe 3Voxtral 3 official release chart · Artificial Analysis weighted WER · republished in Mistral chart· Reported by Mistral AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.2.1%
2Voxtral Mini Transcribe 3Voxtral 3 official release chart · Artificial Analysis weighted WER · republished in Mistral chart· Reported by Mistral AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.2.2%

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.