Competitive Programming on CodeForces
78.3Overall ScoreFiltered
Evaluation results
| Method | Links | |
|---|---|---|
| FilteredBackbone=Qwen 3B, Training Distribution=Numina, Method Category=Selection2026.05 | 78.3 | |
| RandomBackbone=Qwen 3B, Training Distribution=Numina, Method Category=Selection2026.05 | 77.6 | |
| DiversityBackbone=Qwen 3B, Training Distribution=Numina, Method Category=AS2026.05 | 70.6 | |
| DiversityBackbone=Qwen 3B, Training Distribution=MedMCQA, Method Category=AS2026.05 | 67.6 | |
| ConfidenceBackbone=Qwen 3B, Training Distribution=Numina, Method Category=AS2026.05 | 63.9 | |
| DataEnvGymBackbone=Qwen 3B, Training Distribution=MedMCQA, Method Category=Synthesis2026.05 | 55.7 | |
| Answer VarianceBackbone=Qwen 3B, Training Distribution=Numina, Method Category=AS2026.05 | 55 | |
| ProximityBackbone=Qwen 3B, Training Distribution=MedMCQA, Method Category=AS2026.05 | 54 | |
| Gradient NormBackbone=Qwen 3B, Training Distribution=Numina, Method Category=AS2026.05 | 53.7 | |
| ConfidenceBackbone=Qwen 3B, Training Distribution=MedMCQA, Method Category=AS2026.05 | 53.4 | |
| Answer VarianceBackbone=Qwen 3B, Training Distribution=MedMCQA, Method Category=AS2026.05 | 52.3 | |
| Qwen 3BBackbone=Qwen 3B, Method Category=Untrained model2026.05 | 51.5 | |
| ProximityBackbone=Qwen 3B, Training Distribution=Numina, Method Category=AS2026.05 | 50.5 | |
| FormatBackbone=Qwen 3B, Training Distribution=Numina, Method Category=AS2026.05 | 49.7 | |
| RandomBackbone=Qwen 3B, Training Distribution=MedMCQA, Method Category=Selection2026.05 | 46.9 | |
| Gradient NormBackbone=Qwen 3B, Training Distribution=MedMCQA, Method Category=AS2026.05 | 45.8 | |
| DataEnvGymBackbone=Qwen 3B, Training Distribution=Numina, Method Category=Synthesis2026.05 | 41.5 | |
| OriginalBackbone=Qwen 3B, Training Distribution=Numina, Method Category=Synthesis2026.05 | 40.1 | |
| OriginalBackbone=Qwen 3B, Training Distribution=MedMCQA, Method Category=Synthesis2026.05 | 40 | |
| FormatBackbone=Qwen 3B, Training Distribution=MedMCQA, Method Category=AS2026.05 | 38.5 | |
| Qwen3-4B-Instruct-2507 (C/E Weighted (Rev))Model=Qwen3-4B-Instruct-2507, Strategy=C/E Weighted (Rev)2026.02 | 34.66 | |
| Qwen3-4B-Instruct-2507 (Base)Model=Qwen3-4B-Instruct-2507, Strategy=Base2026.02 | 33.63 | |
| Qwen3-4B-Instruct-2507 (Basic Only)Model=Qwen3-4B-Instruct-2507, Strategy=Basic Only2026.02 | 33.11 | |
| Qwen3-4B-Instruct-2507 (B/I Weighted)Model=Qwen3-4B-Instruct-2507, Strategy=B/I Weighted2026.02 | 33.04 | |
| Qwen3-4B-Instruct-2507 (Uniform)Model=Qwen3-4B-Instruct-2507, Strategy=Uniform2026.02 | 31.86 | |
| Qwen3-4B-Instruct-2507 (Edge Only)Model=Qwen3-4B-Instruct-2507, Strategy=Edge Only2026.02 | 31.86 | |
| Qwen3-4B-Instruct-2507 (C/E Weighted)Model=Qwen3-4B-Instruct-2507, Strategy=C/E Weighted2026.02 | 31.79 | |
| Prismatic Syn.Backbone=Qwen 3B, Training Distribution=MedMCQA, Method Category=Synthesis2026.05 | 30.9 | |
| Qwen3-4B-Instruct-2507 (Complex Only)Model=Qwen3-4B-Instruct-2507, Strategy=Complex Only2026.02 | 30.61 | |
| Qwen3-Coder-30B-A3B-Instruct (Base)Model=Qwen3-Coder-30B-A3B-Instruct, Strategy=Base2026.02 | 29.65 | |
| FilteredBackbone=Qwen 3B, Training Distribution=MedMCQA, Method Category=Selection2026.05 | 23.9 | |
| Prismatic Syn.Backbone=Qwen 3B, Training Distribution=Numina, Method Category=Synthesis2026.05 | 23.6 |