加载中...
加载中...
Grok-3 - Reasoning Beta
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Grok-3 - Reasoning Beta currently shows benchmark results led by AIME 2024 (6 / 62, score 93.30), LiveCodeBench (24 / 108, score 79.40), GPQA Diamond (37 / 162, score 84.60). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.
Grok3模型的推理版本,这是当前还未训练完成,是beta版本。
欢迎关注 DataLearner 官方微信,获得最新 AI 技术推送
