language benchmark
ECLeKTic
A multilingual closed-book question answering dataset that evaluates cross-lingual knowledge transfer in large language models across 12 languages, using knowledge-seeking questions based on Wikipedia articles that exist only in one language
Updated Aug 11, 2026
Models8
Model coverage8
MetricScore
EvidenceB
ECLeKTic Ranking
Higher score ranks better on this benchmark.
| 01 | GO | 19.0% | 100.0% | 8 | C | |
| 02 | GO | 16.7% | 85.7% | 8 | C | |
| 03 | GO | 10.3% | 71.4% | 8 | C | |
| 04 | GO | 4.6% | 57.1% | 8 | C | |
| 05 | GO | 2.5% | 42.9% | 8 | C | |
| 06 | GO | 2.5% | 28.6% | 8 | C | |
| 07 | GO | 1.9% | 14.3% | 8 | C | |
| 08 | GO | 1.4% | 0.0% | 8 | C |
ECLeKTic Score Distribution
A closer view of the leading scores on this benchmark.
ECLeKTic Highlights
The leading models and scores on this benchmark.
What is ECLeKTic?
What ECLeKTic measures and how its scores work.
A multilingual closed-book question answering dataset that evaluates cross-lingual knowledge transfer in large language models across 12 languages, using knowledge-seeking questions based on Wikipedia articles that exist only in one language
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- ECLeKTic
- Modality
- text
- Primary category
- language
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- eclektic|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about ECLeKTic.
Which model scores highest on ECLeKTic?
Gemma 3n E4B Instructed is currently ranked first with 19.0%.
What does ECLeKTic measure?
A multilingual closed-book question answering dataset that evaluates cross-lingual knowledge transfer in large language models across 12 languages, using knowledge-seeking questions based on Wikipedia articles that exist only in one language
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
8 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.