Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Group-level distractor generation on Discrete Math 40
Loading...
36.43
Recall
Deepseek-V3
19.3428
23.7789
28.215
32.6511
Aug 15, 2025
Recall
Updated 1mo ago
Evaluation Results
Method
Method
Links
Recall
Deepseek-V3
Framework=MCTS-guided...
2025.08
36.43
Claude-4-Sonnet
Framework=MCTS-guided...
2025.08
34.29
GPT-3.5-turbo
Framework=MCTS-guided...
2025.08
30.71
GPT-4o
Framework=MCTS-guided...
2025.08
29.29
D-GEN
2025.08
28.57
LLaMA-3-70B
Framework=MCTS-guided...
2025.08
28.57
DiVERT
2025.08
20.71
O&A
2025.08
20
Feedback
Search any
task
Search any
task