Competitive Programming on Codeforces (avg@8)
56.1Average Score @8SD-ZERO
Evaluation Results
| Method | Links | |
|---|---|---|
| SD-ZEROBase Model=Qwen3-4B-Instruct2026.04 | 56.1 | |
| SRTBase Model=Qwen3-4B-Instruct2026.04 | 52.7 | |
| GRPOBase Model=Qwen3-4B-Instruct2026.04 | 52.2 | |
| RFTBase Model=Qwen3-4B-Instruct2026.04 | 50.9 | |
| SDFTBase Model=Qwen3-4B-Instruct2026.04 | 49.3 | |
| SFTBase Model=Qwen3-4B-Instruct2026.04 | 49.1 | |
| Qwen3-4B-InstructBase Model=Qwen3-4B-Instruct2026.04 | 48 | |
| SD-ZEROBase Model=Olmo-3-7B-Instruct2026.04 | 43.5 | |
| SRTBase Model=Olmo-3-7B-Instruct2026.04 | 42.8 | |
| RFTBase Model=Olmo-3-7B-Instruct2026.04 | 39.2 | |
| GRPOBase Model=Olmo-3-7B-Instruct2026.04 | 37.1 | |
| SDFTBase Model=Olmo-3-7B-Instruct2026.04 | 33.5 | |
| Olmo-3-7B-InstructBase Model=Olmo-3-7B-Instruct2026.04 | 31.7 | |
| SFTBase Model=Olmo-3-7B-Instruct2026.04 | 31.7 |