Codeforces - Google February 2026 evaluation
Code
Codeforces rating reported in Google's February 2026 Deep Think evaluation, without tools, using one attempt on each of 222 problems from April-October 2025 Codeforces contests with difficulty above 1500 Elo according to clist.by. This contest protocol is distinct from LiveCodeBench Pro's independently computed rating history.
Top models (higher is better)
| Model | Score |
|---|---|
| Gemini 3 Deep Think | 3455 |