Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
AI Tutoring on 50 student queries 1-5 scale (test)
Loading...
4.874
Quality
Premium-only (target)
4.38104
4.50902
4.637
4.76498
Jun 16, 2026
Quality
SE
Correctness
Scaffolding
Delta AIED
Updated 1mo ago
Evaluation Results
Method
Method
Links
Quality
SE
Correctness
Scaffolding
Delta AIED
Premium-only (target)
Role=Reference target
2026.06
4.874
0.023
5
4.64
0
FairTutor
Escalation threshold τ...
2026.06
4.76
0.039
4.94
4.38
0.114
Generic cascade router
2026.06
4.695
0.042
4.92
4.16
0.179
Naive difficulty router
2026.06
4.543
0.061
4.76
3.98
0.331
Low-cost-only
2026.06
4.4
0.08
4.68
3.64
0.474
Feedback
Search any
task
Search any
task