Skip to content

Benchmark

Gbaeval Replay score

Scores are percentages.

Models measured
28
Scores recorded
28
Sources
1
IQ weight
1.21

Score distribution

47%
Mean
55.7%
Median
38.9%
Std dev
0.7%
10th percentile
96.3%
90th percentile
0%
Min
0%100%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.21 for chat models, measured over 28 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)