Group-level Distractor Generation on Eedi Elementary Math 100
31.66RecallDiVERT
Evaluation Results
| Method | Links | |
|---|---|---|
| DiVERT2025.08 | 31.66 | |
| Deepseek-V3Framework=MCTS-guided reasoning reconstruction, Backbone=Deepseek-V32025.08 | 31.1 | |
| Claude-4-SonnetFramework=MCTS-guided reasoning reconstruction, Backbone=Claude-4-Sonnet2025.08 | 28.31 | |
| GPT-4oFramework=MCTS-guided reasoning reconstruction, Backbone=GPT-4o2025.08 | 27.37 | |
| O&A2025.08 | 26.63 | |
| GPT-3.5-turboFramework=MCTS-guided reasoning reconstruction, Backbone=GPT-3.5-turbo2025.08 | 24.39 | |
| LLaMA-3-70BFramework=MCTS-guided reasoning reconstruction, Backbone=LLaMA-3-70B2025.08 | 22.16 | |
| D-GEN2025.08 | 20.48 |