Codeforces
Codeforces: Measures model capability on programming, code generation, code repair, or repository-level software tasks.
14rows
llm_stats_codeforces_scoreprimary metric
2026-05-28sampled
Metadata
Metrics
LLM Stats CodeForces Score, LLM Stats CodeForces Normalized Score
| Rank | Subject | LLM Stats CodeForces Score | Model Match | Provenance | Sampled |
|---|---|---|---|---|---|
| 1 | DeepSeek-V4-Flash-Max | 1 |  DeepSeek V4 Flash deepseek-deepseek-v4-flash | Self-reported | 2026-05-28 |
| 1 | DeepSeek-V4-Pro-Max | 1 | DeepSeek V4 Pro deepseek-deepseek-v4-pro | Self-reported | 2026-05-28 |
| 3 | DeepSeek-V3.2-Speciale | 0.9 | DeepSeek V3.2 Speciale deepseek-deepseek-v3.2-speciale | Self-reported | 2026-05-28 |
| 4 | Qwen3.5-122B-A10B | 0.851 |  Qwen3.5-122B-A10B qwen-qwen3.5-122b-a10b | Self-reported | 2026-05-28 |
| 5 | Qwen3.5-35B-A3B | 0.822 | Qwen3.5-35B-A3B qwen-qwen3.5-35b-a3b | Self-reported | 2026-05-28 |
| 6 | GPT OSS 120B | 0.821 |  gpt-oss-120b openai-gpt-oss-120b | Self-reported | 2026-05-28 |
| 7 | Qwen3.5-27B | 0.807 | Qwen3.5-27B qwen-qwen3.5-27b | Self-reported | 2026-05-28 |
| 8 | DeepSeek-V3.2 | 0.795 | DeepSeek V3.2 deepseek-deepseek-v3.2 | Self-reported | 2026-05-28 |
| 8 | DeepSeek-V3.2 (Thinking) | 0.795 | DeepSeek V3.2 deepseek-deepseek-v3.2 | Self-reported | 2026-05-28 |
| 10 | GPT OSS 20B | 0.7433 | gpt-oss-20b openai-gpt-oss-20b | Self-reported | 2026-05-28 |
| 11 | DeepSeek-V3.2-Exp | 0.707 | DeepSeek V3.2 Exp deepseek-deepseek-v3.2-exp | Self-reported | 2026-05-28 |
| 12 | DeepSeek-V3.1 | 0.697 | DeepSeek V3.1 deepseek-deepseek-chat-v3.1 | Self-reported | 2026-05-28 |
| 13 | Qwen3 32B | 0.659 | Qwen3 32B qwen-qwen3-32b | Self-reported | 2026-05-28 |
| 14 | DeepSeek-R1-0528 | 0.6433 | R1 0528 deepseek-deepseek-r1-0528 | Self-reported | 2026-05-28 |
No matching rows.