Skip to content

Benchmark

LaoBench Lao-7k translation Culture & History 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

58.2
Mean
58
Median
1.4
Std dev
56.6
10th percentile
59.9
90th percentile
56.6
Min
56.659.9
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1GPT 5table: 7, mode: single· LaoBench (arXiv:2511.11334v3) data59.9
2Qwen3 Maxtable: 7, mode: single· LaoBench (arXiv:2511.11334v3) data58
3Gemini 2.5 Protable: 7, mode: single· LaoBench (arXiv:2511.11334v3) data56.6

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.