Mathematical Problem Solving on AMC 22-23
85.7AccuracyselfRef@4
Evaluation results
| Method | Links | ||
|---|---|---|---|
| selfRef@4backbone=GSR-7B2025.08 | 85.7 | 1.1 | |
| maj@5backbone=GSR-7B2025.08 | 84.9 | — | |
| maj@4backbone=GSR-7B2025.08 | 84.6 | — | |
| BoN@4backbone=GSR-7B, Aggregation Model=RM-R1-7B2025.08 | 84.6 | — | |
| Ref@4backbone=GSR-7B, Aggregation Model=Synthesizer-8B2025.08 | 84 | — | |
| BoN@5backbone=GSR-7B, Aggregation Model=SkyworkRM-27B2025.08 | 82.8 | — | |
| BoN@4backbone=GSR-7B, Aggregation Model=SkyworkRM-27B2025.08 | 81.6 | — | |
| BoN@4backbone=GSR-7B, Aggregation Model=RRM-7B2025.08 | 80.4 | — | |
| pass@1backbone=GSR-7B2025.08 | 78.5 | — | |
| BoN@4backbone=Qwen2.5-7B-Instruct (Base), Aggregation Model=SkyworkRM-27B2025.08 | 48 | — | |
| maj@4backbone=Qwen2.5-7B-Instruct (Base)2025.08 | 47.7 | — | |
| selfRef@4backbone=Qwen2.5-7B-Instruct (Base)2025.08 | 47.5 | -0.2 | |
| pass@1backbone=Qwen2.5-7B-Instruct (Base)2025.08 | 43.6 | — |