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
7,941
73% of checked
Has Issues
1,393
13% of checked
Can't Verify
1,569
14% of checkedincl. 276 dead links
Not Yet Checked
0
of 10,903 total
Contradicted
174
Fix now — data may be wrong
Outdated
32
Source has newer info
Accuracy Rate
97%
confirmed / (confirmed + wrong + outdated)
Needs Recheck
0
All up to date
sid_ISfAiImMYg / GSM8K: 96.4
sid_v1e1ZwDwoA / HellaSwag: 84
sid_v1e1ZwDwoA / MMLU: 60.1
sid_v1e1ZwDwoA / HumanEval: 30.5
sid_v1e1ZwDwoA / GSM8K: 40.3
sid_nnv09Wl5OQ / LiveCodeBench: 79.4
sid_nnv09Wl5OQ / Chatbot Arena Elo: 1402
sid_nnv09Wl5OQ / HumanEval: 86.5
sid_nnv09Wl5OQ / GSM8K: 89.3
sid_nnv09Wl5OQ / MMLU-Pro: 79.9
sid_nywmt9QdsA / MathVista: 73.1
sid_nywmt9QdsA / MMLU: 80.1
sid_Gqv7h9oEwA / HellaSwag: 95
sid_Gqv7h9oEwA / GSM8K: 92
sid_Gqv7h9oEwA / MATH: 76.6
sid_Gqv7h9oEwA / MGSM: 90.5
sid_Gqv7h9oEwA / HumanEval: 90.2
sid_Gqv7h9oEwA / MMLU: 88.7
sid_PaKhQQNPkg / MATH: 78.3
sid_PaKhQQNPkg / HumanEval: 89.7
sid_PaKhQQNPkg / MMLU: 92.4
sid_PaKhQQNPkg / Humanity's Last Exam: 44.4
sid_PaKhQQNPkg / ARC-AGI-2: 77.1
sid_PaKhQQNPkg / GPQA Diamond: 94.3
sid_PaKhQQNPkg / MMLU-Pro: 90.99
sid_PaKhQQNPkg / SWE-bench Verified: 80.6
sid_svlbcrT5oQ / MMLU-Pro: 75.9
sid_svlbcrT5oQ / GPQA Diamond: 59.1
sid_svlbcrT5oQ / DROP: 91.6
sid_svlbcrT5oQ / BBH: 87.5
sid_svlbcrT5oQ / MMLU: 88.5
sid_svlbcrT5oQ / HumanEval: 65.2
sid_svlbcrT5oQ / MATH: 61.6
sid_svlbcrT5oQ / GSM8K: 89.3
sid_dHgSM46fMw / GPQA Diamond: 80.9
sid_dHgSM46fMw / SWE-bench Verified: 74.5
sid_y87VxEBBIA / SWE-bench Verified: 73.3
sid_y87VxEBBIA / OSWorld: 50.7
xAI - Footnote 12
xAI - Footnote 11
xAI - Footnote 5
xAI - Footnote 2
xAI - Footnote 1
Will MacAskill - Footnote 19
Will MacAskill - Footnote 18
Will MacAskill - Footnote 17
Will MacAskill - Footnote 10
Will MacAskill - Footnote 9
Will MacAskill - Footnote 8
Will MacAskill - Footnote 7
| Type | Entity | Claim | Verdict | Confidence | Sources | Last Checked | |
|---|---|---|---|---|---|---|---|
| Benchmark Result | Claude 3.5 Sonnet | sid_ISfAiImMYg / GSM8K: 96.4 | confirmed | 95% | 1 | Apr 24, 2026 | |
| Benchmark Result | Mistral | sid_v1e1ZwDwoA / HellaSwag: 84 | confirmed | 95% | 1 | Apr 24, 2026 | |
| Benchmark Result | Mistral | sid_v1e1ZwDwoA / MMLU: 60.1 | confirmed | 98% | 1 | Apr 24, 2026 | |
| Benchmark Result | Mistral | sid_v1e1ZwDwoA / HumanEval: 30.5 | confirmed | 98% | 1 | Apr 24, 2026 | |
| Benchmark Result | Mistral | sid_v1e1ZwDwoA / GSM8K: 40.3 | confirmed | 98% | 1 | Apr 24, 2026 | |
| Benchmark Result | Grok | sid_nnv09Wl5OQ / LiveCodeBench: 79.4 | confirmed | 95% | 1 | Apr 24, 2026 | |
| Benchmark Result | Grok | sid_nnv09Wl5OQ / Chatbot Arena Elo: 1402 | confirmed | 95% | 1 | Apr 24, 2026 | |
| Benchmark Result | Grok | sid_nnv09Wl5OQ / HumanEval: 86.5 | confirmed | 95% | 1 | Apr 24, 2026 | |
| Benchmark Result | Grok | sid_nnv09Wl5OQ / GSM8K: 89.3 | confirmed | 95% | 1 | Apr 24, 2026 | |
| Benchmark Result | Grok | sid_nnv09Wl5OQ / MMLU-Pro: 79.9 | confirmed | 95% | 1 | Apr 24, 2026 | |
| Benchmark Result | GPT-4.1 mini | sid_nywmt9QdsA / MathVista: 73.1 | unverifiable | 85% | 1 | Apr 24, 2026 | |
| Benchmark Result | GPT-4.1 mini | sid_nywmt9QdsA / MMLU: 80.1 | confirmed | 98% | 1 | Apr 24, 2026 | |
| Benchmark Result | GPT | sid_Gqv7h9oEwA / HellaSwag: 95 | confirmed | 95% | 1 | Apr 24, 2026 | |
| Benchmark Result | GPT | sid_Gqv7h9oEwA / GSM8K: 92 | confirmed | 95% | 1 | Apr 24, 2026 | |
| Benchmark Result | GPT | sid_Gqv7h9oEwA / MATH: 76.6 | confirmed | 95% | 1 | Apr 24, 2026 | |
| Benchmark Result | GPT | sid_Gqv7h9oEwA / MGSM: 90.5 | confirmed | 95% | 1 | Apr 24, 2026 | |
| Benchmark Result | GPT | sid_Gqv7h9oEwA / HumanEval: 90.2 | confirmed | 99% | 1 | Apr 24, 2026 | |
| Benchmark Result | GPT | sid_Gqv7h9oEwA / MMLU: 88.7 | confirmed | 98% | 1 | Apr 24, 2026 | |
| Benchmark Result | Gemini | sid_PaKhQQNPkg / MATH: 78.3 | confirmed | 95% | 1 | Apr 24, 2026 | |
| Benchmark Result | Gemini | sid_PaKhQQNPkg / HumanEval: 89.7 | confirmed | 95% | 1 | Apr 24, 2026 | |
| Benchmark Result | Gemini | sid_PaKhQQNPkg / MMLU: 92.4 | confirmed | 95% | 1 | Apr 24, 2026 | |
| Benchmark Result | Gemini | sid_PaKhQQNPkg / Humanity's Last Exam: 44.4 | confirmed | 99% | 1 | Apr 24, 2026 | |
| Benchmark Result | Gemini | sid_PaKhQQNPkg / ARC-AGI-2: 77.1 | confirmed | 98% | 1 | Apr 24, 2026 | |
| Benchmark Result | Gemini | sid_PaKhQQNPkg / GPQA Diamond: 94.3 | confirmed | 98% | 1 | Apr 24, 2026 | |
| Benchmark Result | Gemini | sid_PaKhQQNPkg / MMLU-Pro: 90.99 | confirmed | 98% | 1 | Apr 24, 2026 | |
| Benchmark Result | Gemini | sid_PaKhQQNPkg / SWE-bench Verified: 80.6 | confirmed | 98% | 1 | Apr 24, 2026 | |
| Benchmark Result | DeepSeek Models | sid_svlbcrT5oQ / MMLU-Pro: 75.9 | confirmed | 95% | 1 | Apr 24, 2026 | |
| Benchmark Result | DeepSeek Models | sid_svlbcrT5oQ / GPQA Diamond: 59.1 | confirmed | 99% | 1 | Apr 24, 2026 | |
| Benchmark Result | DeepSeek Models | sid_svlbcrT5oQ / DROP: 91.6 | confirmed | 99% | 1 | Apr 24, 2026 | |
| Benchmark Result | DeepSeek Models | sid_svlbcrT5oQ / BBH: 87.5 | confirmed | 99% | 1 | Apr 24, 2026 | |
| Benchmark Result | DeepSeek Models | sid_svlbcrT5oQ / MMLU: 88.5 | confirmed | 95% | 1 | Apr 24, 2026 | |
| Benchmark Result | DeepSeek Models | sid_svlbcrT5oQ / HumanEval: 65.2 | confirmed | 99% | 1 | Apr 24, 2026 | |
| Benchmark Result | DeepSeek Models | sid_svlbcrT5oQ / MATH: 61.6 | confirmed | 99% | 1 | Apr 24, 2026 | |
| Benchmark Result | DeepSeek Models | sid_svlbcrT5oQ / GSM8K: 89.3 | confirmed | 99% | 1 | Apr 24, 2026 | |
| Benchmark Result | Claude Opus 4.1 | sid_dHgSM46fMw / GPQA Diamond: 80.9 | confirmed | 95% | 1 | Apr 24, 2026 | |
| Benchmark Result | Claude Opus 4.1 | sid_dHgSM46fMw / SWE-bench Verified: 74.5 | confirmed | 99% | 1 | Apr 24, 2026 | |
| Benchmark Result | Claude Haiku 4.5 | sid_y87VxEBBIA / SWE-bench Verified: 73.3 | confirmed | 98% | 1 | Apr 24, 2026 | |
| Benchmark Result | Claude Haiku 4.5 | sid_y87VxEBBIA / OSWorld: 50.7 | unverifiable | 95% | 1 | Apr 24, 2026 | |
| Citation | - | xAI - Footnote 12 | confirmed | 100% | 1 | Apr 3, 2026 | |
| Citation | - | xAI - Footnote 11 | partial | 85% | 1 | Apr 3, 2026 | |
| Citation | - | xAI - Footnote 5 | partial | 80% | 1 | Apr 3, 2026 | |
| Citation | - | xAI - Footnote 2 | partial | 85% | 1 | Apr 3, 2026 | |
| Citation | - | xAI - Footnote 1 | contradicted | 50% | 1 | Apr 3, 2026 | |
| Citation | - | Will MacAskill - Footnote 19 | contradicted | 60% | 1 | Apr 3, 2026 | |
| Citation | - | Will MacAskill - Footnote 18 | confirmed | 100% | 1 | Apr 3, 2026 | |
| Citation | - | Will MacAskill - Footnote 17 | confirmed | 100% | 1 | Apr 3, 2026 | |
| Citation | - | Will MacAskill - Footnote 10 | confirmed | 100% | 1 | Apr 3, 2026 | |
| Citation | - | Will MacAskill - Footnote 9 | contradicted | 50% | 1 | Apr 3, 2026 | |
| Citation | - | Will MacAskill - Footnote 8 | confirmed | 100% | 1 | Apr 3, 2026 | |
| Citation | - | Will MacAskill - Footnote 7 | confirmed | 100% | 1 | Apr 3, 2026 |
Data from source_check_verdicts table. Click a row to view detailed evidence.