ResearchDatasetsMulti-Domain Evaluation SuiteMulti-Domain Evaluation SuiteFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsCross-domain language model performance evaluationMulti-domain Evaluation Suite (mid-training evaluation)60.4Math Score4Multi-Domain Language Modeling and ReasoningMulti-Domain Evaluation Suite General, Code, Math 50B tokens (mid-training)59.13General Accuracy3
Cross-domain language model performance evaluationMulti-domain Evaluation Suite (mid-training evaluation)60.4Math Score4
Multi-Domain Language Modeling and ReasoningMulti-Domain Evaluation Suite General, Code, Math 50B tokens (mid-training)59.13General Accuracy3