Skip to content

Benchmark

Earnings-22 · Keyphrase recall · Without context

Scores are percentages. Higher is better.

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

Score distribution

81.4%
Mean
81.4%
Median
0%
Std dev
81.4%
10th percentile
81.4%
90th percentile
81.4%
Min

Leaderboard

#ModelScore
1Voxtral Small Transcribe 3Voxtral 3 official release chart · keyphrase recall · without context bias· Reported by Mistral AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.81.4%

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.