Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Coding benchmark
Codeforces Rating. Every model the catalog carries a published Codeforces value for, ranked by that value.
Competitive-programming rating reported for DeepSeek-V4 thinking-mode evaluations. 8 models in the ModelChoice catalog have a published value.
Each point is a model with a published Codeforces value and complete token prices, on the 75% input / 25% output blend. Frontier models are spaced evenly along the cost axis.
8 models with a published Codeforces value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Rating |
|---|---|---|---|
| 1 | DeepSeek | 3471.0 | |
| 2 | DeepSeek | 3206.0 | |
| 2 | DeepSeek | 3206.0 |
What the benchmark measures and how its value is published, from the source’s own record.
Codeforces (Codeforces Rating) is a coding benchmark published by DeepSeek-V4 Technical Report. Competitive-programming rating reported for DeepSeek-V4 thinking-mode evaluations. Its evaluation set is described by the source as competitive programming contests. The source rates its difficulty as elite competitive programming.
Each model's result is published by DeepSeek-V4 Technical Report as rating. ModelChoice prints that value to 1 decimal place, exactly as published, and never converts or rescales it. This page ranks the 8 models that carry a published value, highest value first; a model the source never scored is left out rather than ranked at zero. The source does not state whether a higher value is the better result, so neither does this page.
| 4 | DSdots3-note Preview | Dots Studio | 3056.0 |
| 5 | DeepSeek | 3052.0 |
| 6 | DeepSeek | 1930.0 |
| 7 | DeepSeek | 1633.0 |
| 8 | DeepSeek | 1481.0 |
Evidence key: ObservedLast good
Rows are ordered by the value DeepSeek-V4 Technical Report published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.