20.7推論強度: Extra High140169.6 強度別None 11.7Medium 20.0Extra High 20.7
AA Intelligence IndexについてAA Intelligence Indexについて詳しく
27.4%推論強度: Extra High76.0%56.1% τ³-Bankingについてτ³-Bankingについて詳しく
76.7%推論強度: Extra High67.6140538.2%61.2%26.6%6.3%0.0%41.0%47.8% 強度別None 29.7%Medium 67.3%Extra High 76.7%
Long Context ReasoningについてLong Context Reasoningについて詳しく
141811.7%37.7%3.1%96.9%56.0 Arena Text FactualityについてArena Text Factualityについて詳しく
0.5%推論強度: Extra High146046.8100552.4%60.7%42.4%56.147.2%70.849.2%1450 Terminal-Bench 4.0についてTerminal-Bench 4.0について詳しく
1363141375.9%1336138762.577.1%135267.2 Arena Writing, Literature & LanguageについてArena Writing, Literature & Languageについて詳しく
28.3%推論強度: Extra High9.3%142581.7%87.8%91.044.9%12.2%5.0%1415143181.125.9%6.3%51.5%5.7%30.0%9.0%80.3%36.9 強度別None 4.1%Medium 15.9%Extra High 28.3%
Humanity's Last ExamについてHumanity's Last Examについて詳しく
119666.1% Arena VisionについてArena Visionについて詳しく
13441373142114371413140088.0%71.9%72.2%71.6%96.0%92.5%83.0%74.0%100.0%56.5%34.0%77.0%8.7%74.0%73.0%67.0%97.0%51.0%48.8% Arena KoreanについてArena Koreanについて詳しく
