Benchmark
CodeForces Benchmark
What is CodeForces?
A competitive programming benchmark using problems from the CodeForces platform. The benchmark evaluates code generation capabilities of LLMs on algorithmic…
- Modality
- text
- Evaluates
- math, reasoning
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 17
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/codeforces?top_n=500
CodeForces results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| DeepSeek-R1-0528 | DeepSeek | 0.6433 | 2025-05-28 | evidence |
| DeepSeek-V3.1 | DeepSeek | 0.697 | 2025-01-10 | evidence |
| DeepSeek-V3.2 | DeepSeek | 0.795 | 2025-12-01 | evidence |
| DeepSeek-V3.2 (Thinking) | DeepSeek | 0.795 | 2025-12-01 | evidence |
| DeepSeek-V3.2-Exp | DeepSeek | 0.707 | 2025-09-29 | evidence |
| DeepSeek-V3.2-Speciale | DeepSeek | 0.9 | 2025-12-01 | evidence |
| DeepSeek-V4-Flash-0423 | DeepSeek | 0.9387 | 2026-04-23 | evidence |
| DeepSeek-V4-Flash-Max | DeepSeek | 1.0 | 2026-04-23 | evidence |
| DeepSeek-V4-Pro-Max | DeepSeek | 1.0 | 2026-04-23 | evidence |
| DiffusionGemma 26B-A4B | 0.4763 | 2026-06-10 | evidence | |
| Gemma 4 12B | 0.553 | 2026-05-23 | evidence | |
| GPT OSS 120B | OpenAI | 0.821 | 2025-08-05 | evidence |
| GPT OSS 20B | OpenAI | 0.7433 | 2025-08-05 | evidence |
| Qwen3 32B | Qwen | 0.659 | 2025-04-29 | evidence |
| Qwen3.5-122B-A10B | Qwen | 0.851 | 2026-02-24 | evidence |
| Qwen3.5-27B | Qwen | 0.807 | 2026-02-24 | evidence |
| Qwen3.5-35B-A3B | Qwen | 0.822 | 2026-02-24 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.