Project AURIONAI Use-Cases Research & Innovation

Codeforces rating

Competitive programming Elo-style rating

codingactive
3scores
3models
0independent
0maintainer-run
3vendor-reported

Definition

Version
not in the notes
Category
coding
Maintainer
Codeforces
Status
active
Home page
not in the notes

Sources

  1. deepseek-ai/DeepSeek-V4.1-Flash , Hugging Face huggingface.co https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash
  2. DeepSeek V4-Pro Review: Benchmarks, Pricing & Architecture blog.buildfastwithai.com https://blog.buildfastwithai.com/deepseek-v4-pro-review-2026

Scores at a Glance

Score in rating

Higher is better for this unit.

1DeepSeekDeepSeek-V4.1-FlashDeepSeek
3,471 rating
vendor-reported2DeepSeekDeepSeek-V4-ProDeepSeek
3,206 rating
vendor-reported
01,0002,0003,0004,000
Where this comes from
Each bar is one model, with its most independent recorded score. Hatched bars are vendor-reported; the word beside each bar says who ran it. Settings and dates differ between rows; the Scores table below has every result.

Scores

3 of 3 scores shown codeforces-scores.csv
ModelScoreWho ran itSettingView or populationDateSource
DeepSeekDeepSeek-V4.1-Flash3,471 ratingvendor-reported–––huggingface.co
Google DeepMindGemini 3 Deep Think3,455 Elovendor-reportedUpdated Deep ThinkGemini 3 Deep Think upgrade post12 Feb 2026blog.google
DeepSeekDeepSeek-V4-Pro3,206 ratingvendor-reported–––blog.buildfastwithai.com
Where this comes from
Scores from different settings, harnesses or dates are not directly comparable; the row says which. Sorted by score, highest first, as a reading aid, not a ranking.

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Codeforces Rating", https://aurion.semai.id/benchmarks/codeforces/, records of October 2026.