新 SOOHAK 基準測試暴露 AI 數學缺陷
名為 soohak 的新基準測試顯示，前沿模型在研究級數學上得分低於 30%，且無法識別無解問題。
developed by carnegie mellon, eleutherai, and seoul national university, soohak features 340 research-level problems and 99 unsolvable 'refusal' tasks to test calibration. while gemini 3 pro achieved 61 percent coverage on a subset compared to human mathematicians' 51 percent, the benchmark reveals that increased compute improves solving but not the ability to admit a problem has no answer.