Gemini 2.0 Flash Thinking on MMLU (Massive Multitask Language Understanding): Score Breakdown

Gemini 2.0 Flash Thinking × MMLU (Massive Multitask Language Understanding)

スコア内訳

モデルランキングスコア
#11 / 20586.5

パフォーマンス分析

Gemini 2.0 Flash Thinking achieves 86.5 on MMLU (Massive Multitask Language Understanding).