Skip to content

Benchmark

MMLU-ProX 5-shot CoT VI

Scores are percentages. Higher is better.

Models measured
7
Scores recorded
8
Sources
1
IQ weight
0.27

Score distribution

73.7%
Mean
73.4%
Median
2%
Std dev
71.4%
10th percentile
76.3%
90th percentile
71.4%
Min
71.4%76.7%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.27 for chat models, measured over 7 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: MMLU-ProX: Xuan et al., arXiv:2503.10497. Public project-page results; no results licence stated.