Skip to content

Benchmark

ECLeKTic

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

Models measured
6
Scores recorded
6
Sources
1
IQ weight
0.81

Score distribution

9.1%
Mean
10.3%
Median
6.8%
Std dev
2.5%
10th percentile
19%
90th percentile
1.4%
Min
1.4%19%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.81 for chat models, measured over 6 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Gemma 3n E4B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim19%
2Gemma 3 27B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim16.7%
3Gemma 3 12B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim10.3%
4Gemma 3 4B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim4.6%
5Gemma 3n E2b It· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim2.5%
6Gemma 3 1b it· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim1.4%

Data credits: Data by LLM Stats