xAI , a company founded by famous businessman Elon Musk in March 2023 , announced the Grok Grok-1.5 model for its chat bot called Grok . This model, which is shared to be much improved compared to the first version, is said to be more performant than GPT-4 developed by OpenAI . Here are the details about the Grok-1.5 model…
Grok-1.5 model outperforms GPT-4!
xAI announced the Grok-1.5 model via its official website . According to the information shared by the company, the new model can now process visuals, including documents, diagrams, charts, screenshots and photographs.
When we look at the examples shared about Grok-1.5, which is stated to be able to compete with multi-mode models, we see that the model stands out with its capabilities such as converting the table to CSV, solving the error in the code, converting the diagram code and explaining the meme.
Sony announced the most downloaded PlayStation games last month. Popular PS4, PS5 and PS VR games were included in the list.
Grok-1.5 achieved a success rate of 53.6 percent in MMMU tests conducted by xAI . By comparison, GPT-4 achieved 56.8 percent success in the same tests . However, in math-related tests , Grok-1.5 surpassed GPT-4 , achieving a success rate of 52.8 percent . In addition, xAI ‘s new model, AI2D, challenged its competitors in text reading and comprehension and real-world understanding tests.
Benchmark results of Grok-1.5 and competing models are as follows;
| Benchmark | Grok-1.5V | GPT-4V | Claude 3 Sonnet | Close 3 Work | Gemini Pro 1.5 |
|---|---|---|---|---|---|
| MMMU (Multidisciplinary) | 53.6% | 56.8% | 53.1% | 59.4% | 58.5% |
| Mathematics | 52.8% | 49.9% | 47.9% | 50.5% | 52.1% |
| AI2D | 88.3% | 78.2% | 88.7% | 88.1% | 80.3% |
| reading text | 78.1% | 78.0% | – | – | 73.5% |
| ChartQA | 76.1% | 78.5% | 81.1% | 80.8% | 81.3% |
| Documents | 85.6% | 88.4% | 89.5% | 89.3% | 86.5% |
| Real World Understanding | 68.7% | 61.4% | 51.9% | 49.8% | 67.5% |
xAI announced that it will soon start testing the Grok-1.5 model with users and integrate it into the Grok chatbot in X. For those who don’t know, you need to be an X Premium subscriber to access this bot .
