Skip to content

Benchmark

PashtoBench translation Pashto to English BLEU

Multilingual benchmarks compare model performance across languages. Higher scores are better.

Models measured
4
Scores recorded
4
Sources
1
IQ weight
No weight published

Score distribution

38.1
Mean
70
Median
34.3
Std dev
2.3
10th percentile
74.6
90th percentile
2.3
Min
2.374.6
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Claude Sonnet 5direction: pbt-en· PashtoBench v1.0 data docs74.6
2GPT 4odirection: pbt-en· PashtoBench v1.0 data docs70
3Qwen2.5 72B Instructdirection: pbt-en· PashtoBench v1.0 data docs5.3
4Llama 3.3 70B Instructdirection: pbt-en· PashtoBench v1.0 data docs2.3

Data credits: PashtoBench v1.0, Jawad Noori. Public results/scores numbers; code MIT and data/ CC BY 4.0 grants do not name results/, so no results licence is asserted.