"At the ICPC, only correct solutions earn points, and the time it takes to come up with the solution affects the final score. Gemini reached the upper rankings quickly, completing eight problems correctly in just 45 minutes. After 677 minutes, Gemini 2.5 Deep Think had 10 correct answers, securing a second-place finish among the university teams. You can take a look at all of Gemini's solutions on GitHub, but Google points to Problem C as especially impressive."
"According to Google, there are an infinite number of possible configurations for the flubber reservoirs, making it challenging to find the optimal setup. Gemini tackled the problem by assuming that each reservoir had a priority value, which allowed the model to find the most efficient configuration using a dynamic programming algorithm. After 30 minutes of churning on this problem, Deep Think used nested ternary search to pin down the correct values."
Gemini 2.5 Deep Think competed in the ICPC, completing eight problems in 45 minutes and finishing with 10 correct answers after 677 minutes to take second place among university teams. Google highlights Problem C, a multi-dimensional optimization challenge involving flubber reservoir configurations that stumped every human team. Gemini assumed reservoir priority values and applied dynamic programming, then used nested ternary search after 30 minutes to refine values. Google also ran Gemini on past ICPC sets and reported gold-level performance for 2023 and 2024. Google suggests such capabilities could benefit fields like semiconductors and biotechnology. Power costs were not disclosed.
Read at Ars Technica
Unable to calculate read time
Collection
[
|
...
]