All Source Checks
Automated source checking of wiki data against original sources. Each record is checked against one or more external sources to confirm accuracy.
View internal dashboard with coverage & action queue →Verified Correct
65
97% of checked
Has Issues
0
0% of checked
Can't Verify
2
3% of checked
Not Yet Checked
0
of 67 total
Contradicted
0
None found
Outdated
0
All current
Accuracy Rate
100%
confirmed / (confirmed + wrong + outdated)
Needs Recheck
0
All up to date
sid_PaKhQQNPkg / MMLU-Pro: 90.99
sid_PaKhQQNPkg / SWE-bench Verified: 80.6
sid_PaKhQQNPkg / Humanity's Last Exam: 44.4
sid_PaKhQQNPkg / ARC-AGI-2: 77.1
sid_PaKhQQNPkg / GPQA Diamond: 94.3
sid_svlbcrT5oQ / BBH: 87.5
sid_svlbcrT5oQ / GPQA Diamond: 59.1
sid_svlbcrT5oQ / DROP: 91.6
sid_svlbcrT5oQ / MMLU-Pro: 75.9
sid_svlbcrT5oQ / HumanEval: 65.2
sid_svlbcrT5oQ / GSM8K: 89.3
sid_svlbcrT5oQ / MATH: 61.6
sid_svlbcrT5oQ / MMLU: 88.5
sid_dHgSM46fMw / SWE-bench Verified: 74.5
sid_dHgSM46fMw / GPQA Diamond: 80.9
sid_y87VxEBBIA / OSWorld: 50.7
sid_y87VxEBBIA / SWE-bench Verified: 73.3
Data from source_check_verdicts table. Click a row to view detailed evidence.