List your company

MMLU

Benchmarks

TaskDatasetSOTA resultTrendResults
MMLU
91.2MMLU General Knowledge Accuracy
General Knowledge on MMLU (Accuracy) performance trend
373
MMLU-Pro
92.86Accuracy
Reasoning on MMLU-Pro performance trend
264
MMLU-Pro
82.3Accuracy
General Reasoning on MMLU-Pro (Accuracy) performance trend
213
MMLU
85.93Accuracy
Knowledge on MMLU performance trend
171
MMLU 5-shot (test)
74.2Accuracy
Language Understanding on MMLU (5-shot, test) performance trend
149