Index
sid_tppPAkJqjQ / GSM8K: 95
Verdictconfirmed99%
1 check · 4/24/2026Inline sourcing: confirmed
Our claim
entire record- Benchmark
- fjjBrOI3p2
- Model
- Claude Opus 4.5
- Score
- 95
- Unit
- percent
- Date
- November 24, 2025
- Notes
- GSM8K - Grade school math reasoning
Source evidence
1 src · 1 checkconfirmed99%inline-submission · 4/24/2026
Case № 1PqZPHUnMtFiled 4/24/2026Confidence 99%