Benchmark
ECLeKTic
A multilingual closed-book question answering dataset that evaluates cross-lingual knowledge transfer in large language models across 12 languages, using…
- Modality
- text
- Categories
- reasoning, language
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 8
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Gemma 3 12B | 0.103 | 2025-03-12 | evidence | |
| Gemma 3 1B | 0.014 | 2025-03-12 | evidence | |
| Gemma 3 27B | 0.167 | 2025-03-12 | evidence | |
| Gemma 3 4B | 0.046 | 2025-03-12 | evidence | |
| Gemma 3n E2B Instructed | 0.025 | 2025-06-26 | evidence | |
| Gemma 3n E2B Instructed LiteRT (Preview) | 0.025 | 2025-05-20 | evidence | |
| Gemma 3n E4B Instructed | 0.19 | 2025-06-26 | evidence | |
| Gemma 3n E4B Instructed LiteRT Preview | 0.019 | 2025-05-20 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.