Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-task Model Evaluation on AIME24, AIME25, HMMT25, HE+, MBPP+ Average
Loading...
58.4
Average Accuracy
Teacher Model
10.768
23.134
35.5
47.866
Jun 21, 2026
Average Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Accuracy
Teacher Model
Model=Qwen3-4B-Instruc...
2026.06
58.4
IW-OPD
Student Model=Qwen3-4B...
2026.06
55.3
IW-OPD10
Student Model=Qwen3-4B...
2026.06
55.1
OPD
Student Model=Qwen3-4B...
2026.06
54.3
OPD10
Student Model=Qwen3-4B...
2026.06
54
IW-OPD
Student Model=Qwen3-1....
2026.06
39.1
Base
Student Model=Qwen3-4B...
2026.06
38.9
IW-OPD10
Student Model=Qwen3-1....
2026.06
38.1
OPD
Student Model=Qwen3-1....
2026.06
37.9
OPD10
Student Model=Qwen3-1....
2026.06
36.8
Base
Student Model=Qwen3-1....
2026.06
28.7
IW-OPD
Student Model=Qwen3-0....
2026.06
21.9
IW-OPD10
Student Model=Qwen3-0....
2026.06
20.6
OPD
Student Model=Qwen3-0....
2026.06
20
OPD10
Student Model=Qwen3-0....
2026.06
18.6
Base
Student Model=Qwen3-0....
2026.06
12.6
Feedback
Search any
task
Search any
task
