Skip to content
Longterm Wiki has not been actively maintained since May 2026. Some data is still updated occasionally, but please don't rely on this site being current or accurate.
Longterm Wiki

Llama on MATH: 73.8

benchmark-resultVerified

Child of MATH

Metadata

Source Tablebenchmark_results
Source IDtVEnqaUPCi
Source URLwww.ibm.com/think/news/meta-releases-llama-3-1-models-405b-parameter-variant
ParentMATH
Children—
CreatedApr 24, 2026, 7:16 PM
UpdatedApr 24, 2026, 7:16 PM
SyncedApr 24, 2026, 7:16 PM

Record Data

idtVEnqaUPCi
benchmarkIdq6rR1sbyZG
modelIdLlama(ai-model)
score73.8
unitpercent
date2024-07-23
sourceUrlwww.ibm.com/think/news/meta-releases-llama-3-1-models-405b-parameter-variant
notesLlama 3.1 405B Instruct, 0-shot chain-of-thought
testedByunknown
testedByOrgId—
evaluationDate—
methodologyNotes—

Source Check Verdicts

confirmed99% confidence

Last checked: 4/29/2026

1 → confirmed

Debug info

Thing ID: tVEnqaUPCi

Source Table: benchmark_results

Source ID: tVEnqaUPCi

Parent Thing ID: q6rR1sbyZG