Benchmark
LaoBench Lao-7k translation Society & Law BLEU (zero-shot)
Multilingual benchmarks compare model performance across languages. Higher scores are better.
- Models and systems measured
- 12
- Scores recorded
- 13
- Sources
- 1
- IQ weight
- 1.29
Score distribution
- 20
- Mean
- 21.7
- Median
- 6
- Std dev
- 16
- 10th percentile
- 24.8
- 90th percentile
- 0.69
- Min
This benchmark has a weight of 1.29 for chat models, measured over 10 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model or system | Score |
|---|---|---|
| 1 | Gemini 2.5 Protable: 3, mode: single· LaoBench (arXiv:2511.11334v3) data | 26.2 |
| 2 | Claude Opus 4.1table: 3, mode: single· LaoBench (arXiv:2511.11334v3) data | 24.8 |
| 3 | Claude Sonnet 4.5table: 3, mode: single· LaoBench (arXiv:2511.11334v3) data | 22.8 |
| 4 | DeepSeek V3.2 Exptable: 3, mode: Non-Thinking· LaoBench (arXiv:2511.11334v3) data | 22.5 |
| 5 | Qwen3 235B A22B Instruct 2507table: 3, mode: single· LaoBench (arXiv:2511.11334v3) data | 21.8 |
| 6 | Qwen3 Maxtable: 3, mode: single· LaoBench (arXiv:2511.11334v3) data | 21.7 |
| 7 | GPT 5table: 3, mode: single· LaoBench (arXiv:2511.11334v3) data | 21 |
| 8 | DeepSeek V3.2 Exptable: 3, mode: Thinking· LaoBench (arXiv:2511.11334v3) data | 20.6 |
| 9 | Qwen 3 235B A22Btable: 3, mode: single· LaoBench (arXiv:2511.11334v3) data | 20.4 |
| 10 | Qwen3 Next 80B A3B Instructtable: 3, mode: single· LaoBench (arXiv:2511.11334v3) data | 16 |
| 11 | Ling Mini 2.0table: 3, mode: single· LaoBench (arXiv:2511.11334v3) data | 0.69 |
Not ranked
The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.
| Model or system | Score |
|---|---|
| Qwen3-PlusNon-Thinkingtable: 3, mode: Non-Thinking· LaoBench (arXiv:2511.11334v3) data | 21.7 |
| Qwen3-PlusThinkingtable: 3, mode: Thinking· LaoBench (arXiv:2511.11334v3) data | 20.3 |