ResearchDatasetsWizardMath + LLaMA-2WizardMath + LLaMA-2FollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsFingerprint VerificationWizardMath-7B-V1.0 + LLaMA-2-7B-CHAT (Merged Model) Task Arithmetic alpha=0.5 (test)100VSR27
Fingerprint VerificationWizardMath-7B-V1.0 + LLaMA-2-7B-CHAT (Merged Model) Task Arithmetic alpha=0.5 (test)100VSR27