Codeforces
Can the model complete substantial programming work under this benchmark's agent setup?
Top rankings
One row per model, using its best reported score across effort settings.
| Rank | Model | Best score | Best reported setting |
|---|---|---|---|
| 1 | DeepSeek V4.1 FlashDeepSeek | 3471 | Reported configurationDeepSeek report1 value · 1 reportSep 10, 2026 · source |
| 2 | DeepSeek V4 ProDeepSeek | 3206 | max effortDeepSeek report2 values · 1 reportApr 26, 2026 · source |
| 3 | GPT-5.4OpenAI | 3168 | xhigh effortDeepSeek report1 value · 1 reportApr 26, 2026 · source |
| 4 | DeepSeek-V4-FlashDeepSeek | 3052 | max effortDeepSeek report2 values · 1 reportApr 26, 2026 · source |
| 5 | Gemini 3.1 ProGoogle | 3052 | high effortDeepSeek report1 value · 1 reportApr 26, 2026 · source |
Effort curve
Every sourced cost-linked effort value for this exact version. Lines connect complete sweeps only.
Definition and comparison boundarypublic methodology
Can the model complete substantial programming work under this benchmark's agent setup?
Software implementation, debugging, or repository work under the published evaluation protocol. Higher is better. This benchmark reports points rather than percent correct.
Harness, tools, prompts, attempt count, and benchmark version can materially change the result. Compare within one reporting context.
DeepSeek's official V4.1-Flash release table reports a Codeforces rating of 3471; no contest set or evaluation setup is printed. Rating scale as printed in the DeepSeek V4 model card; dashes are omitted.
Method / source