Skip to content

Benchmark

Dubesor Reason

Scores are percentages.

Models measured
218
Scores recorded
261
Sources
1
IQ weight
1.50

Score distribution

44.7%
Mean
42.8%
Median
24.3%
Std dev
11.2%
10th percentile
76.9%
90th percentile
0%
Min
0%93.3%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.50 for chat models, measured over 218 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

Showing 251–261 of 261 results.