Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Science Reasoning on MMLU Pro
Loading...
66.49
Accuracy
EAPO
35.758
43.7365
51.715
59.6935
Jun 29, 2026
Accuracy
Updated 25d ago
Evaluation Results
Method
Method
Links
Accuracy
EAPO
Model=Qwen-3-8B-Base
2026.06
66.49
MOPD
Model=Qwen-3-8B-Base
2026.06
65.99
OPD
Model=Qwen-3-8B-Base
2026.06
65.91
DAPO
Model=Qwen-3-8B-Base
2026.06
65.29
GRPO
Model=Qwen-3-8B-Base
2026.06
64.71
EAPO
Model=Qwen-2.5-Math-7B
2026.06
47.57
EAPO w/o sIS
Model=Qwen-2.5-Math-7B
2026.06
47.35
Trajectory Replay
Model=Qwen-2.5-Math-7B
2026.06
46.5
DAPO
Model=Qwen-2.5-Math-7B
2026.06
44.09
MOPD
Model=Qwen-2.5-Math-7B
2026.06
43.81
OPD
Model=Qwen-2.5-Math-7B
2026.06
43.34
GRPO
Model=Qwen-2.5-Math-7B
2026.06
36.94
Feedback
Search any
task
Search any
task
