Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Human Evaluation on Education subset
Loading...
85
Win Rate
MENTOR
57.96
64.98
72
79.02
Nov 10, 2025
Win Rate
Tie Rate
Loss Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Win Rate
Tie Rate
Loss Rate
MENTOR
Backbone=DeepSeek-R1
2025.11
85
13
2
MENTOR
Backbone=GPT-4o
2025.11
78
22
0
MENTOR
Backbone=Qwen3-235B
2025.11
59
35
6
Feedback
Search any
task
Search any
task
