Skip to content
Longterm Wiki
benchmark-result

Llama on MMLU: 87.3

Child of MMLU

Metadata

Source Tablebenchmark_results
Source IDiCGCi9oy5E
Source URLwww.ibm.com/think/news/meta-releases-llama-3-1-models-405b-parameter-variant
ParentMMLU
Children
CreatedApr 24, 2026, 7:16 PM
UpdatedApr 24, 2026, 7:16 PM
SyncedApr 24, 2026, 7:16 PM

Record Data

idiCGCi9oy5E
benchmarkIdizV3Xk98se
modelIdLlama(ai-model)
score87.3
unitpercent
date2024-07-23
sourceUrlwww.ibm.com/think/news/meta-releases-llama-3-1-models-405b-parameter-variant
notesLlama 3.1 405B Instruct, 5-shot evaluation

Source Check Verdicts

confirmed99% confidence

Last checked: 4/24/2026

Inline sourcing: confirmed

Debug info

Thing ID: iCGCi9oy5E

Source Table: benchmark_results

Source ID: iCGCi9oy5E

Parent Thing ID: izV3Xk98se