Skip to content

Benchmark

Thematic Generalization V2 (Lech Mazur)

Scores are percentages.

Models measured
22
Scores recorded
29
Sources
1
IQ weight
1.76

Score distribution

57.2%
Mean
63.3%
Median
18.1%
Std dev
27.1%
10th percentile
77.4%
90th percentile
20.3%
Min
20.3%80.6%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.76 for chat models, measured over 22 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard