Skip to content

Benchmark

LaoBench Lao-7k translation Society & Law chrF++ (zero-shot)

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

Models measured
3
Scores recorded
3
Sources
1
IQ weight
No weight published

Score distribution

51.8
Mean
52.4
Median
1.1
Std dev
50.3
10th percentile
52.8
90th percentile
50.3
Min
50.352.8
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Gemini 2.5 Protable: 7, mode: single· LaoBench (arXiv:2511.11334v3) data52.8
2Qwen3 Maxtable: 7, mode: single· LaoBench (arXiv:2511.11334v3) data52.4
3GPT 5table: 7, mode: single· LaoBench (arXiv:2511.11334v3) data50.3

Data credits: LaoBench, BAAI et al., arXiv:2511.11334v3. Cited numeric results only. arXiv non-exclusive distribution notice establishes no results reuse grant; dataset Apache licence is not a results grant.