Skip to content
Longterm Wiki
benchmark-result

Gemini on HumanEval: 89.7

Child of HumanEval

Metadata

Source Tablebenchmark_results
Source IDYrqdjSCYpO
ParentHumanEval
Children
CreatedApr 24, 2026, 7:00 PM
UpdatedApr 24, 2026, 7:00 PM
SyncedApr 24, 2026, 7:00 PM

Record Data

idYrqdjSCYpO
benchmarkIdvxX2rorgxU
modelIdGemini(ai-model)
score89.7
unitpercent
date2026-02-19
sourceUrl
notesGemini Pro on HumanEval code generation

Source Check Verdicts

confirmed95% confidence

Last checked: 4/24/2026

Inline sourcing: confirmed

Debug info

Thing ID: YrqdjSCYpO

Source Table: benchmark_results

Source ID: YrqdjSCYpO

Parent Thing ID: vxX2rorgxU