Skip to content

Benchmark

LaoBench Lao-7k Knowledge Application Nature & Science accuracy (zero-shot)

Multilingual benchmarks compare model performance across languages. Scores are percentages. Higher is better.

Models and systems measured
14
Scores recorded
15
Sources
1
IQ weight
1.23

Score distribution

61.5%
Mean
61.5%
Median
16.8%
Std dev
29%
10th percentile
75.8%
90th percentile
25%
Min
25%98%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.23 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 systemScore
1GPT 5table: 3, mode: single· LaoBench (arXiv:2511.11334v3) data75.8%
2Gemini 2.5 Protable: 3, mode: single· LaoBench (arXiv:2511.11334v3) data70.4%
3DeepSeek V3.2 Exptable: 3, mode: Thinking· LaoBench (arXiv:2511.11334v3) data69.4%
4Claude Sonnet 4.5table: 3, mode: single· LaoBench (arXiv:2511.11334v3) data69.1%
5Claude Opus 4.1table: 3, mode: single· LaoBench (arXiv:2511.11334v3) data68.5%
6Qwen3 Maxtable: 3, mode: single· LaoBench (arXiv:2511.11334v3) data63.4%
7Qwen3 235B A22B Instruct 2507table: 3, mode: single· LaoBench (arXiv:2511.11334v3) data61.5%
8DeepSeek V3.2 Exptable: 3, mode: Non-Thinking· LaoBench (arXiv:2511.11334v3) data58.3%
9Qwen 3 235B A22Btable: 3, mode: single· LaoBench (arXiv:2511.11334v3) data57.6%
10Qwen3 Next 80B A3B Instructtable: 3, mode: single· LaoBench (arXiv:2511.11334v3) data55.7%
11Ling Mini 2.0table: 3, mode: single· LaoBench (arXiv:2511.11334v3) data29%

Not ranked

The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.

Model or systemScore
Human Expertstable: 3, mode: single· LaoBench (arXiv:2511.11334v3) data98%
Qwen3-PlusNon-Thinkingtable: 3, mode: Non-Thinking· LaoBench (arXiv:2511.11334v3) data60.5%
Qwen3-PlusThinkingtable: 3, mode: Thinking· LaoBench (arXiv:2511.11334v3) data60.5%
Random Choicetable: 3, mode: single· LaoBench (arXiv:2511.11334v3) data25%

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.