Skip to content
Longterm Wiki
benchmark-result

GPT on HumanEval: 90.2

Child of HumanEval

Metadata

Source Tablebenchmark_results
Source IDG2od24L4z9
ParentHumanEval
Children
CreatedApr 24, 2026, 7:04 PM
UpdatedApr 24, 2026, 7:04 PM
SyncedApr 24, 2026, 7:04 PM

Record Data

idG2od24L4z9
benchmarkIdvxX2rorgxU
modelIdGPT(ai-model)
score90.2
unitpercent
date2024-05-19
sourceUrl
notesGPT-4o scores on HumanEval code generation benchmark

Source Check Verdicts

confirmed99% confidence

Last checked: 4/24/2026

Inline sourcing: confirmed

Debug info

Thing ID: G2od24L4z9

Source Table: benchmark_results

Source ID: G2od24L4z9

Parent Thing ID: vxX2rorgxU