Skip to content
Longterm Wiki
benchmark-result

Claude 3.7 Sonnet on GSM8K: 96.4

Child of GSM8K

Metadata

Source Tablebenchmark_results
Source IDx8gFrNhDk1
ParentGSM8K
Children
CreatedApr 24, 2026, 7:38 PM
UpdatedApr 24, 2026, 7:38 PM
SyncedApr 24, 2026, 7:38 PM

Record Data

idx8gFrNhDk1
benchmarkIdfjjBrOI3p2
modelIdClaude 3.7 Sonnet(ai-model)
score96.4
unitpercent
date2025-02-24
sourceUrl
notesGSM8K grade school math

Source Check Verdicts

confirmed99% confidence

Last checked: 4/24/2026

Inline sourcing: confirmed

Debug info

Thing ID: x8gFrNhDk1

Source Table: benchmark_results

Source ID: x8gFrNhDk1

Parent Thing ID: fjjBrOI3p2