Index
sid_tppPAkJqjQ / SimpleQA: 36
Verdictconfirmed99%
1 check · 4/24/2026Inline sourcing: confirmed
Our claim
entire record- Benchmark
- 1O19f6j13Z
- Model
- Claude Opus 4.5
- Score
- 36
- Unit
- percent
- Date
- November 24, 2025
- Notes
- SimpleQA - factual accuracy benchmark for straightforward questions
Source evidence
1 src · 1 checkconfirmed99%inline-submission · 4/24/2026
Case № TFSWZuy9Y8Filed 4/24/2026Confidence 99%