Math on Math (test)
80.9AccuracyOPCD
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| OPCDModel=Qwen3-8B2026.02 | 80.9 | 80.8 | |
| Context Distill.Model=Qwen3-8B2026.02 | 79.5 | 80.4 | |
| In-ContextModel=Qwen3-8B2026.02 | 79 | — | |
| Base ModelModel=Qwen3-8B2026.02 | 75 | 81.3 | |
| wd1Backbone=Dream-7B, Seq Len=512, Zero-shot=true2025.12 | 50.5 | — | |
| ESPOBackbone=Dream-7B, Seq Len=512, Zero-shot=true2025.12 | 50.3 | — | |
| diffu-GRPOBackbone=Dream-7B, Seq Len=512, Zero-shot=true2025.12 | 48.9 | — | |
| DreamBackbone=Dream-7B, Seq Len=512, Zero-shot=true2025.12 | 48 | — | |
| wd1Backbone=Dream-7B, Seq Len=256, Zero-shot=true2025.12 | 47.4 | — | |
| ESPOBackbone=Dream-7B, Seq Len=256, Zero-shot=true2025.12 | 47.4 | — | |
| diffu-GRPOBackbone=Dream-7B, Seq Len=256, Zero-shot=true2025.12 | 46.9 | — | |
| ESPOBackbone=Dream-7B, Seq Len=Avg., Zero-shot=true2025.12 | 46 | — | |
| wd1Backbone=Dream-7B, Seq Len=Avg., Zero-shot=true2025.12 | 45.8 | — | |
| DreamBackbone=Dream-7B, Seq Len=256, Zero-shot=true2025.12 | 45.7 | — | |
| diffu-GRPOBackbone=Dream-7B, Seq Len=Avg., Zero-shot=true2025.12 | 45.1 | — | |
| DreamBackbone=Dream-7B, Seq Len=Avg., Zero-shot=true2025.12 | 44 | — | |
| ESPOBackbone=LLaDA-8B, Seq Len=512, Zero-shot=true2025.12 | 43.4 | — | |
| diffu-GRPOBackbone=LLaDA-8B, Seq Len=512, Zero-shot=true2025.12 | 41.7 | — | |
| LLaDABackbone=LLaDA-8B, Seq Len=512, Zero-shot=true2025.12 | 41.4 | — | |
| ESPOBackbone=Dream-7B, Seq Len=128, Zero-shot=true2025.12 | 40.3 | — | |
| wd1Backbone=LLaDA-8B, Seq Len=512, Zero-shot=true2025.12 | 39.8 | — | |
| ESPOBackbone=LLaDA-8B, Seq Len=Avg., Zero-shot=true2025.12 | 39.5 | — | |
| wd1Backbone=Dream-7B, Seq Len=128, Zero-shot=true2025.12 | 39.5 | — | |
| diffu-GRPOBackbone=Dream-7B, Seq Len=128, Zero-shot=true2025.12 | 39.4 | — | |
| ESPOBackbone=LLaDA-8B, Seq Len=256, Zero-shot=true2025.12 | 39 | — | |
| DreamBackbone=Dream-7B, Seq Len=128, Zero-shot=true2025.12 | 38.2 | — | |
| diffu-GRPOBackbone=LLaDA-8B, Seq Len=Avg., Zero-shot=true2025.12 | 37.7 | — | |
| wd1Backbone=LLaDA-8B, Seq Len=256, Zero-shot=true2025.12 | 37.7 | — | |
| LLaDABackbone=LLaDA-8B, Seq Len=Avg., Zero-shot=true2025.12 | 37 | — | |
| wd1Backbone=LLaDA-8B, Seq Len=Avg., Zero-shot=true2025.12 | 36.9 | — | |
| diffu-GRPOBackbone=LLaDA-8B, Seq Len=256, Zero-shot=true2025.12 | 36.6 | — | |
| ESPOBackbone=LLaDA-8B, Seq Len=128, Zero-shot=true2025.12 | 36 | — | |
| LLaDABackbone=LLaDA-8B, Seq Len=256, Zero-shot=true2025.12 | 35.2 | — | |
| diffu-GRPOBackbone=LLaDA-8B, Seq Len=128, Zero-shot=true2025.12 | 34.9 | — | |
| LLaDABackbone=LLaDA-8B, Seq Len=128, Zero-shot=true2025.12 | 34.4 | — | |
| wd1Backbone=LLaDA-8B, Seq Len=128, Zero-shot=true2025.12 | 33.3 | — |