Skip to content

Benchmark

LaoBench Lao-7k K12 Education Thinking & Philosophy 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
1.26

Score distribution

71.1%
Mean
75.4%
Median
17.6%
Std dev
34.6%
10th percentile
82.2%
90th percentile
25%
Min
25%97.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.26 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
1Gemini 2.5 Protable: 3, mode: single· LaoBench (arXiv:2511.11334v3) data82.2%
2GPT 5table: 3, mode: single· LaoBench (arXiv:2511.11334v3) data80.8%
3Claude Sonnet 4.5table: 3, mode: single· LaoBench (arXiv:2511.11334v3) data79.7%
4Claude Opus 4.1table: 3, mode: single· LaoBench (arXiv:2511.11334v3) data78.3%
5Qwen 3 235B A22Btable: 3, mode: single· LaoBench (arXiv:2511.11334v3) data77.1%
6Qwen3 Maxtable: 3, mode: single· LaoBench (arXiv:2511.11334v3) data76.3%
7DeepSeek V3.2 Exptable: 3, mode: Thinking· LaoBench (arXiv:2511.11334v3) data75.4%
8Qwen3 235B A22B Instruct 2507table: 3, mode: single· LaoBench (arXiv:2511.11334v3) data74.7%
9Qwen3 Next 80B A3B Instructtable: 3, mode: single· LaoBench (arXiv:2511.11334v3) data68.3%
10DeepSeek V3.2 Exptable: 3, mode: Non-Thinking· LaoBench (arXiv:2511.11334v3) data68.1%
11Ling Mini 2.0table: 3, mode: single· LaoBench (arXiv:2511.11334v3) data34.6%

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) data97.3%
Qwen3-PlusNon-Thinkingtable: 3, mode: Non-Thinking· LaoBench (arXiv:2511.11334v3) data74.1%
Qwen3-PlusThinkingtable: 3, mode: Thinking· LaoBench (arXiv:2511.11334v3) data74.5%
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.