| language-modelling-on-lambada | ModernBERT-base-chat-v0.1 | #48 | Accuracy: 49.3 |
| code-generation-on-mbpp | Dream-Instruct (reasoning SFT) | #123 | Accuracy: 45.53 |
| mathematical-reasoning-on-math-500 | LLaDA-Instruct (reasoning SFT) | #131 | Accuracy: 35.40 |
| arithmetic-reasoning-on-gsm8k | LLaDA-Instruct (reasoning SFT) | #152 | Accuracy: 80.59 |
| math-word-problem-solving-on-math | Qwen3-0.6B-diffusion-bd3lm-v0.1 | #168 | Accuracy: 13.9 |
| sentence-completion-on-hellaswag | ModernBERT-large-chat-v0.1 | #189 | Accuracy: 45.0 |
| sentence-completion-on-hellaswag | Qwen3-0.6B-diffusion-mdlm-v0.1 | #195 | Accuracy: 42.1 |