Skip to content

Benchmark

MMLU-ProX 5-shot CoT UR

Scores are percentages. Higher is better.

Models measured
7
Scores recorded
8
Sources
1
IQ weight
0.37

Score distribution

71.3%
Mean
70.8%
Median
3.1%
Std dev
68.3%
10th percentile
76.1%
90th percentile
68%
Min
68%76.2%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.37 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.