Skip to content

Benchmark

MMLU-ProX 5-shot CoT ES

Scores are percentages. Higher is better.

Models measured
7
Scores recorded
8
Sources
1
IQ weight
0.29

Score distribution

76.1%
Mean
76.9%
Median
3.1%
Std dev
72.8%
10th percentile
80.2%
90th percentile
72.2%
Min
72.2%80.7%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.29 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.