Skip to content

Benchmark

Arena ELO Text Factuality - Longer Query

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

Models measured
160
Scores recorded
179
Sources
1
IQ weight
2.18

Score distribution

1,450.6
Mean
1,455.4
Median
42.5
Std dev
1,387.5
10th percentile
1,494.5
90th percentile
1,307.2
Min
1,307.21,538.9
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.18 for chat models, measured over 160 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

Showing 151–179 of 179 results.

Data credits: LMArena, CC BY 4.0 (licence)