Skip to content

Benchmark

Persian-family Sentiment Accuracy (Iranian Persian SentiPers (Formal), zero-shot)

Multilingual benchmarks compare model performance across languages. Scores are percentages. Higher is better.

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

Score distribution

54.9%
Mean
61.8%
Median
6.9%
Std dev
48%
10th percentile
61.8%
90th percentile
48%
Min
48%61.8%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Qwen2.5 3B Instructtable: 5, task: Sentiment, metric: Accuracy, subset: Iranian Persian SentiPers (Formal)· Persian, Dari and Tajiki paper data docs61.8%
2Qwen2.5 1.5B Instructtable: 5, task: Sentiment, metric: Accuracy, subset: Iranian Persian SentiPers (Formal)· Persian, Dari and Tajiki paper data docs48%

Data credits: Noor Mairukh Khan Arnob and Abu Bakar Siddique Mahi. One Language, Three of Its Voices, SilkRoadNLP 2026, ©2026 ACL, CC BY 4.0. Numeric/protocol extract from Tables 2, 5 and 6; language and pooled subsets retained. (licence)