Baidu ERNIE Agent Tops the Leaderboard of Renowned LLM Benchmark PinchBench v2
Baidu
Baidu ERNIE agent model topped the PinchBench v2 ranking, surpassing GPT-4 and other models. This achievement underscores Baidu's leadership in AI agents.
Baidu's ERNIE task agent model (文心助手任务Agent) has taken first place in the popular large language model benchmark PinchBench v2. This result demonstrates significant progress by Baidu in the field of AI agents, which are capable of performing complex tasks. During testing, the model outperformed competitors, including OpenAI's GPT-4. PinchBench v2 is a benchmark test that evaluates models' abilities to solve problems using tools and planning.
Source: Baidu ERNIE (GNews) —
original