Skip to content

Benchmark

PashtoBench translation Pashto to English chrF++

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

62.3
Mean
84.4
Median
25.6
Std dev
24.8
10th percentile
87.5
90th percentile
24.8
Min
24.887.5
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Claude Sonnet 5direction: pbt-en· PashtoBench v1.0 data docs87.5
2GPT 4odirection: pbt-en· PashtoBench v1.0 data docs84.4
3Llama 3.3 70B Instructdirection: pbt-en· PashtoBench v1.0 data docs52.4
4Qwen2.5 72B Instructdirection: pbt-en· PashtoBench v1.0 data docs24.8

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.