Skip to content

Benchmark

TydiQA

Multilingual benchmarks compare model performance across languages. Scores are percentages.

Models measured
2
Scores recorded
2
Sources
1
IQ weight
No weight published

Score distribution

31.6%
Mean
31.7%
Median
0.1%
Std dev
31.5%
10th percentile
31.7%
90th percentile
31.5%
Min
31.5%31.7%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Llama 4 Maverick· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim31.7%
2Llama 4 Scout· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim31.5%

Data credits: Data by LLM Stats