List your company

Group-level Distractor Generation on Eedi Elementary Math 100

31.66RecallDiVERT
20.032823.051426.0729.0886Aug 15, 2025

Evaluation results

MethodLinks
DiVERT2025.0831.66
Deepseek-V3Framework=MCTS-guided reasoning reconstruction, Backbone=Deepseek-V32025.0831.1
Claude-4-SonnetFramework=MCTS-guided reasoning reconstruction, Backbone=Claude-4-Sonnet2025.0828.31
GPT-4oFramework=MCTS-guided reasoning reconstruction, Backbone=GPT-4o2025.0827.37
O&A2025.0826.63
GPT-3.5-turboFramework=MCTS-guided reasoning reconstruction, Backbone=GPT-3.5-turbo2025.0824.39
LLaMA-3-70BFramework=MCTS-guided reasoning reconstruction, Backbone=LLaMA-3-70B2025.0822.16
D-GEN2025.0820.48