Mathematics on GSM8K 0 (test)
83.7AccuracyESPO
Evaluation Results
| Method | Links | |
|---|---|---|
| ESPOBackbone=LLaDA-8B, Seq Len=512, Zero-shot=true2025.12 | 83.7 | |
| wd1Backbone=Dream-7B, Seq Len=512, Zero-shot=true2025.12 | 82.9 | |
| wd1Backbone=Dream-7B, Seq Len=256, Zero-shot=true2025.12 | 82.4 | |
| wd1Backbone=LLaDA-8B, Seq Len=512, Zero-shot=true2025.12 | 82.3 | |
| ESPOBackbone=LLaDA-8B, Seq Len=256, Zero-shot=true2025.12 | 82.3 | |
| ESPOBackbone=Dream-7B, Seq Len=256, Zero-shot=true2025.12 | 82.3 | |
| ESPOBackbone=LLaDA-8B, Seq Len=Avg., Zero-shot=true2025.12 | 82 | |
| ESPOBackbone=Dream-7B, Seq Len=512, Zero-shot=true2025.12 | 82 | |
| diffu-GRPOBackbone=Dream-7B, Seq Len=256, Zero-shot=true2025.12 | 81.9 | |
| diffu-GRPOBackbone=Dream-7B, Seq Len=512, Zero-shot=true2025.12 | 81.7 | |
| DreamBackbone=Dream-7B, Seq Len=256, Zero-shot=true2025.12 | 81.3 | |
| ESPOBackbone=Dream-7B, Seq Len=Avg., Zero-shot=true2025.12 | 81.3 | |
| diffu-GRPOBackbone=LLaDA-8B, Seq Len=512, Zero-shot=true2025.12 | 81.2 | |
| wd1Backbone=LLaDA-8B, Seq Len=256, Zero-shot=true2025.12 | 80.8 | |
| DreamBackbone=Dream-7B, Seq Len=512, Zero-shot=true2025.12 | 80.7 | |
| wd1Backbone=Dream-7B, Seq Len=Avg., Zero-shot=true2025.12 | 80.5 | |
| LLaDABackbone=LLaDA-8B, Seq Len=512, Zero-shot=true2025.12 | 80.2 | |
| diffu-GRPOBackbone=Dream-7B, Seq Len=Avg., Zero-shot=true2025.12 | 80.2 | |
| wd1Backbone=LLaDA-8B, Seq Len=Avg., Zero-shot=true2025.12 | 80.1 | |
| ESPOBackbone=LLaDA-8B, Seq Len=128, Zero-shot=true2025.12 | 80 | |
| ESPOBackbone=Dream-7B, Seq Len=128, Zero-shot=true2025.12 | 79.6 | |
| DreamBackbone=Dream-7B, Seq Len=Avg., Zero-shot=true2025.12 | 79.3 | |
| diffu-GRPOBackbone=LLaDA-8B, Seq Len=256, Zero-shot=true2025.12 | 78.1 | |
| diffu-GRPOBackbone=LLaDA-8B, Seq Len=Avg., Zero-shot=true2025.12 | 78 | |
| wd1Backbone=LLaDA-8B, Seq Len=128, Zero-shot=true2025.12 | 77.2 | |
| diffu-GRPOBackbone=Dream-7B, Seq Len=128, Zero-shot=true2025.12 | 77 | |
| wd1Backbone=Dream-7B, Seq Len=128, Zero-shot=true2025.12 | 76.3 | |
| LLaDABackbone=LLaDA-8B, Seq Len=256, Zero-shot=true2025.12 | 76.2 | |
| LLaDABackbone=LLaDA-8B, Seq Len=Avg., Zero-shot=true2025.12 | 75.9 | |
| DreamBackbone=Dream-7B, Seq Len=128, Zero-shot=true2025.12 | 75.8 | |
| diffu-GRPOBackbone=LLaDA-8B, Seq Len=128, Zero-shot=true2025.12 | 74.6 | |
| LLaDABackbone=LLaDA-8B, Seq Len=128, Zero-shot=true2025.12 | 71.3 |