A benchmark that uses competitive-programming problems to evaluate code generation and algorithmic reasoning.
Browse the latest scores, model modes, release dates, and parameter sizes for CodeForces.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
| Rank | Model | License | |||
|---|---|---|---|---|---|
 Gemini 3 Deep Think - 2620 Thinking Enabled | 3455.00 | 2026-02-13 | Unknown | Closed | |
 DeepSeek-V4-Pro Thinking Level · Max | 3206.00 | 2026-04-24 | 1600B | Free Commercial | |
DeepSeek-V4-Flash Thinking Level · Max | 3052.00 | 2026-04-24 | 284B | Free Commercial | |
4 | DeepSeek-V4-Pro Thinking Level · High | 2919.00 | 2026-04-24 | 1600B | Free Commercial |
5 | DeepSeek-V4-Flash Thinking Level · High | 2816.00 | 2026-04-24 | 284B | Free Commercial |
6 |  OpenAI o4 - mini Thinking EnabledTools | 2719.00 | 2025-04-16 | Unknown | Closed |
7 | DeepSeek V3.2 Speciale Thinking Enabled | 2701.00 | 2025-12-01 | Unknown | Free Commercial |
8 | GPT OSS 120B Thinking EnabledTools | 2622.00 | 2025-08-06 | 11.7B | Free Commercial |
9 | GPT OSS 20B Thinking EnabledTools | 2516.00 | 2025-08-06 | 21B | Free Commercial |
10 | GPT OSS 120B Thinking Enabled | 2463.00 | 2025-08-06 | 11.7B | Free Commercial |
11 | DeepSeek V3.2 Thinking Enabled | 2386.00 | 2025-12-01 | 671B | Free Commercial |
12 | GPT OSS 20B Thinking Enabled | 2230.00 | 2025-08-06 | 21B | Free Commercial |
13 | OpenAI o3-mini Thinking Enabled | 2073.00 | 2025-01-31 | Unknown | Closed |
14 |  Qwen3-32B Thinking Enabled | 1977.00 | 2025-04-28 | 32B | Free Commercial |
15 | Qwen3.5-27B Thinking Enabled | 1899.00 | 2026-02-25 | 27B | Free Commercial |
16 | Qwen3-32B Standard Mode | 1353.00 | 2025-04-28 | 32B | Free Commercial |
