- AA-Omniscience Accuracy17,9%#139
- Humanity's Last Exam22,6%#95
- Terminal-Bench 4.00%#96
- AA-LCR73,7%#91
- SciCode42,4%#94
- CritPt2,6%#91
- AA-AnalystAgent16,3%#22
- τ²-Bench Banking38,6%#21
- APEX-Agents27,4%#6
Ling-3.0-flash-FinMediana
Dati di Artificial Analysis