Benchmark Result·i5f76T7Z3K·Record·Profile

sid_ISfAiImMYg / GSM8K: 96.4

Verdictconfirmed95%

· 4/24/2026

Inline sourcing: confirmed

Our claim

entire record

Benchmark: fjjBrOI3p2
Model: Claude 3.5 Sonnet
Score: 96.4
Unit: percent
Date: June 21, 2024
Notes: Grade school math word problems, multi-step reasoning

Source evidence

0 src · 0 checks

No evidence on file.

Case № i5f76T7Z3KFiled 4/24/2026Confidence 95%