Competitive programming rating from Codeforces, the world's largest competitive programming platform. Models are evaluated on algorithmic problem-solving contests.
This definition has not completed editorial and provenance review. Verify its metric, version, source, and evaluation configuration upstream before using it for a model-selection decision.
Well-calibrated difficulty across a wide range. Tests algorithmic thinking, data structures, and optimization under time pressure.
Rating scale (800–2800) is not a percentage. Older problems may be in training data. Does not test software engineering skills.
Higher is better. Codeforces rating (800=beginner, 1600=expert, 2400+=grandmaster).
Rating scale (800–2800) is not a percentage.
| # | Model | Score |
|---|---|---|
| 1 | 2800.0 | |
| 2 | 2800.0 | |
| 3 | 2800.0 | |
| 4 | 2719.0 | |
| 5 | 2706.0 | |
| 6 | 2701.0 | |
| 7 | 2700.0 | |
| 8 | 2700.0 | |
| 9 | 2650.0 | |
| 10 | 2650.0 | |
| 11 | 2650.0 | |
| 12 | 2650.0 | |
| 13 | 2620.0 | |
| 14 | 2537.0 | |
| 15 | 2537.0 | |
| 16 | 2537.0 | |
| 17 | 2537.0 | |
| 18 | 2512.0 | |
| 19 | 2386.0 | |
| 20 | 2386.0 | |
| 21 | 2350.0 | |
| 22 | 2350.0 | |
| 23 | 2200.0 | |
| 24 | 2200.0 | |
| 25 | 2150.0 | |
| 26 | 2130.0 | |
| 27 | 2130.0 | |
| 28 | 2100.0 | |
| 29 | 2100.0 | |
| 30 | 2070.0 | |
| 31 | 2070.0 | |
| 32 | 2056.0 | |
| 33 | 2056.0 | |
| 34 | 2029.0 | |
| 35 | 2020.0 | |
| 36 | 2020.0 | |
| 37 | 2020.0 | |
| 38 | 2010.0 | |
| 39 | 2010.0 | |
| 40 | 2010.0 | |
| 41 | 2001.0 | |
| 42 | 1995.0 | |
| 43 | 1995.0 | |
| 44 | 1985.0 | |
| 45 | 1985.0 | |
| 46 | 1974.0 | |
| 47 | 1974.0 | |
| 48 | 1974.0 | |
| 49 | 1930.0 | |
| 50 | 1930.0 |