Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on AIME24 (Accuracy)
Loading...
90.31
Accuracy
Qwen3-30B-A3B-Thinking-2507
0.5476
23.8513
47.155
70.4587
Dec 15, 2025
Jan 8, 2026
Feb 2, 2026
Feb 27, 2026
Mar 23, 2026
Apr 17, 2026
May 12, 2026
Accuracy
Updated 21d ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen3-30B-A3B-Thinking-2507
2025.12
90.31
QwenLong-L1.5-30B-A3B
2025.12
90
80/20
Base Model=Qwen2.5-7B-...
2026.05
16.25
PAPO
Base Model=Qwen2.5-14B...
2026.05
15.83
PAPO
Base Model=Qwen2.5-7B-...
2026.05
14.58
DAPO
Base Model=Qwen2.5-7B-...
2026.05
13.75
Ent-Reg
Base Model=Qwen2.5-14B...
2026.05
13.75
80/20
Base Model=Qwen2.5-14B...
2026.05
13.33
Ent-Reg
Base Model=Qwen2.5-7B-...
2026.05
12.91
DAPO
Base Model=Qwen2.5-14B...
2026.05
12.5
Base
Base Model=Qwen2.5-14B...
2026.05
6.67
Base
Base Model=Qwen2.5-7B-...
2026.05
4
Feedback
Search any
task
Search any
task