Salesforce test: Gemini 2.5 Pro solves only 58% of business tasks
The Salesforce CRMArena-Pro test shows that even leading artificial intelligence models face serious limitations when solving everyday business tasks.
Imagine: the flagship model Gemini 2.5 Pro successfully handles only 58% of requests with a single query. And what happens with multi-step dialogue? Efficiency rapidly drops to 35%!
CRMArena-Pro tests large language models under real conditions of sales, customer service and pricing. Researchers created 4280 unique tasks across 19 types of business operations using synthetic Salesforce data.
Particularly revealing are the results in multi-step dialogues — a key element of any business interaction. Almost half of Gemini 2.5 Pro’s failed attempts are related to inability to request critically important information. Models that ask more clarifying questions demonstrate significantly better results.
The highest performance was achieved in automating simple workflows — 83% success in routing support service requests. However, tasks requiring deep text understanding or following complex rules remain a serious challenge for modern artificial intelligence technologies.
Autor: AIvengo
For 5 years I have been working with machine learning and artificial intelligence. And this field never ceases to amaze, inspire and interest me.
Paradise for introverts: AI will talk to company employeesGoogle released a new feature and now artificial intelligence can call local companies on your behalf. To find out information about prices and service availability. You no longer need to pick up the phone yourself and talk to employees. This is exactly what an introvert's paradise looks like.
OpenAI combined ChatGPT, Deep Research and Operator in one agentOpenAI company introduced ChatGPT Agent. A powerful combination of ChatGPT, Deep Research and Operator in a unified solution. The working principle is maximally simple. You set a goal, for example, send emails, create tables, buy tickets or book hotels. ChatGPT Agent independently breaks this goal into separate tasks, navigates to needed websites, searches for information and fills forms. Before critically important actions such as payment, publication or sending, the agent necessarily requests your confirmation.
Only 1 programmer in the world could beat OpenAI's AIImagine a world where artificial intelligence competes with the best programmers on the planet. Such a confrontation took place at the prestigious AtCoder World Tour Finals tournament. This is one of the most elite programming competitions in the world, where it's extremely difficult to get in.
