external benchmark
Vals MMLU-Pro mirror leaderboard
Vals-hosted MMLU-Pro mirror. Every model the catalog carries a published Vals MMLU-Pro mirror value for, ranked by that value.
Categoryexternal
MeasureAccuracy score
TasksMMLU-Pro subject splits
DifficultyProfessional academic reasoning
Published byVals MMLU-Pro
Vals AI hosted MMLU-Pro view with subject-level task splits.
No model in the catalog has a published Vals MMLU-Pro mirror score.
The benchmark is defined by Vals MMLU-Pro, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.