Skip to content

Benchmark

Arena ELO Text Factuality - Industry Software and It Services

People compare model answers and choose which they prefer. Higher scores are better.

Models measured
162
Scores recorded
182
Sources
1
IQ weight
2.15

Score distribution

1,476.5
Mean
1,480.3
Median
36.5
Std dev
1,425.2
10th percentile
1,517.7
90th percentile
1,338.8
Min
1,338.81,546.5
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.15 for chat models, measured over 162 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

Showing 151–182 of 182 results.

Data credits: LMArena, CC BY 4.0 (licence)